This dataset stores LoRA expert pools and gating network weights from multi-task fine-tuning experiments on various base models (Phi-2, Gemma-2, Llama-3.2, Pythia-410M, Qwen2.5-0.5B, SmolLM-360M).
Dataset Card
This dataset stores LoRA expert pools and gating network weights from multi-task fine-tuning experiments on various base models (Phi-2, Gemma-2, Llama-3.2, Pythia-410M, Qwen2.5-0.5B, SmolLM-360M). - legacy/{model}/{runname}/ — runs from the original experimental campaign (2024-12 → 2025-01), with checkpoints at steps 500, 1000,..., finalmodel and bestmodel. - New baseline + Gated runs (2026-05+) are uploaded at the top level following the paper-001 pipeline convention. WIP — Master's thesis research artifacts.
Excerpt from the card by Helain ZIMMERMANN.
Details
- Repository
- Helain/gated-lora-experiments
- Publisher
- Helain ZIMMERMANN
- Task category
- Not stated by the source
- Tags
- Not stated by the source
- Size category
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 34a565da49cd6b17a0bc369f69eb1510ecf5f714
- Last updated
- 2026-10-12
Files
2,688 files, 35.6 GB in total.
Every file (first 2,688)
| File | Type | Size | SHA-256 |
|---|---|---|---|
| legacy/gemma2/exp2_gated_2experts_seed1/best_model/training_state.json | Data | 96 B | — |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-1000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-1500/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-2000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-2500/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-3000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-3500/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-4000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-500/training_state.json | Data | 96 B | — |
| legacy/gemma2/exp2_gated_2experts_seed1/final_model/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp2_gated_2experts_seed1/final_results.json | Data | 260 B | — |
| legacy/gemma2/exp2_gated_2experts_seed1/visualizations/exp2_gated_2experts_seed1_analysis.json | Data | 4.8 KB | — |
| legacy/gemma2/exp2_gated_2experts_seed2/best_model/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-1000/training_state.json | Data | 98 B | — |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-1500/training_state.json | Data | 98 B | — |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-2000/training_state.json | Data | 98 B | — |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-2500/training_state.json | Data | 98 B | — |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-3000/training_state.json | Data | 98 B | — |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-3500/training_state.json | Data | 98 B | — |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-4000/training_state.json | Data | 98 B | — |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-500/training_state.json | Data | 96 B | — |
| legacy/gemma2/exp2_gated_2experts_seed2/final_model/training_state.json | Data | 98 B | — |
| legacy/gemma2/exp2_gated_2experts_seed2/final_results.json | Data | 260 B | — |
| legacy/gemma2/exp2_gated_2experts_seed2/visualizations/exp2_gated_2experts_seed2_analysis.json | Data | 4.8 KB | — |
| legacy/gemma2/exp2_gated_2experts_seed3/best_model/training_state.json | Data | 96 B | — |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-1000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-1500/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-2000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-2500/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-3000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-3500/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-4000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-500/training_state.json | Data | 95 B | — |
| legacy/gemma2/exp2_gated_2experts_seed3/final_model/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp2_gated_2experts_seed3/final_results.json | Data | 260 B | — |
| legacy/gemma2/exp2_gated_2experts_seed3/visualizations/exp2_gated_2experts_seed3_analysis.json | Data | 4.8 KB | — |
| legacy/gemma2/exp3_gated_3experts_seed1/best_model/training_state.json | Data | 96 B | — |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-1000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-1500/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-2000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-2500/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-3000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-3500/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-4000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-500/training_state.json | Data | 96 B | — |
| legacy/gemma2/exp3_gated_3experts_seed1/final_model/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp3_gated_3experts_seed1/final_results.json | Data | 260 B | — |
| legacy/gemma2/exp3_gated_3experts_seed1/visualizations/exp3_gated_3experts_seed1_analysis.json | Data | 6.3 KB | — |
| legacy/gemma2/exp3_gated_3experts_seed2/best_model/training_state.json | Data | 96 B | — |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-1000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-1500/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-2000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-2500/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-3000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-3500/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-4000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-500/training_state.json | Data | 96 B | — |
| legacy/gemma2/exp3_gated_3experts_seed2/final_model/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp3_gated_3experts_seed2/final_results.json | Data | 259 B | — |
| legacy/gemma2/exp3_gated_3experts_seed2/visualizations/exp3_gated_3experts_seed2_analysis.json | Data | 6.3 KB | — |
| legacy/gemma2/exp3_gated_3experts_seed3/best_model/training_state.json | Data | 96 B | — |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-1000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-1500/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-2000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-2500/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-3000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-3500/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-4000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-500/training_state.json | Data | 96 B | — |
| legacy/gemma2/exp3_gated_3experts_seed3/final_model/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp3_gated_3experts_seed3/final_results.json | Data | 261 B | — |
| legacy/gemma2/exp3_gated_3experts_seed3/visualizations/exp3_gated_3experts_seed3_analysis.json | Data | 6.3 KB | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/best_model/training_state.json | Data | 96 B | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-1000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-1500/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-2000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-2500/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-3000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-3500/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-4000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-500/training_state.json | Data | 96 B | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/final_model/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/final_results.json | Data | 260 B | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/visualizations/exp4_gated_loadbalancing_seed1_analysis.json | Data | 6.3 KB | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/best_model/training_state.json | Data | 96 B | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-1000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-1500/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-2000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-2500/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-3000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-3500/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-4000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-500/training_state.json | Data | 96 B | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/final_model/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/final_results.json | Data | 259 B | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/visualizations/exp4_gated_loadbalancing_seed2_analysis.json | Data | 6.3 KB | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/best_model/training_state.json | Data | 96 B | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-1000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-1500/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-2000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-2500/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-3000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-3500/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-4000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-500/training_state.json | Data | 96 B | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/final_model/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/final_results.json | Data | 259 B | — |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/visualizations/exp4_gated_loadbalancing_seed3_analysis.json | Data | 6.3 KB | — |
| legacy/gemma2/exp5_gated_topk_seed1/best_model/training_state.json | Data | 96 B | — |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-1000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-1500/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-2000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-2500/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-3000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-3500/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-4000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-500/training_state.json | Data | 96 B | — |
| legacy/gemma2/exp5_gated_topk_seed1/final_model/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp5_gated_topk_seed1/final_results.json | Data | 259 B | — |
| legacy/gemma2/exp5_gated_topk_seed1/visualizations/exp5_gated_topk_seed1_analysis.json | Data | 6.3 KB | — |
| legacy/gemma2/exp5_gated_topk_seed2/best_model/training_state.json | Data | 96 B | — |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-1000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-1500/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-2000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-2500/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-3000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-3500/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-4000/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-500/training_state.json | Data | 96 B | — |
| legacy/gemma2/exp5_gated_topk_seed2/final_model/training_state.json | Data | 97 B | — |
| legacy/gemma2/exp5_gated_topk_seed2/final_results.json | Data | 259 B | — |
| legacy/gemma2/exp5_gated_topk_seed2/visualizations/exp5_gated_topk_seed2_analysis.json | Data | 6.3 KB | — |
| legacy/gemma2/exp5_gated_topk_seed3/best_model/training_state.json | Data | 95 B | — |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-1000/training_state.json | Data | 96 B | — |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-1500/training_state.json | Data | 96 B | — |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-2000/training_state.json | Data | 96 B | — |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-2500/training_state.json | Data | 96 B | — |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-3000/training_state.json | Data | 96 B | — |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-3500/training_state.json | Data | 96 B | — |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-4000/training_state.json | Data | 96 B | — |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-500/training_state.json | Data | 95 B | — |
| legacy/gemma2/exp5_gated_topk_seed3/final_model/training_state.json | Data | 96 B | — |
| legacy/gemma2/exp5_gated_topk_seed3/final_results.json | Data | 259 B | — |
| legacy/gemma2/exp5_gated_topk_seed3/visualizations/exp5_gated_topk_seed3_analysis.json | Data | 6.3 KB | — |
| legacy/llama32/exp4_gated_loadbalancing_seed1/best_model/training_state.json | Data | 97 B | — |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-1000/training_state.json | Data | 98 B | — |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-1500/training_state.json | Data | 98 B | — |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-2000/training_state.json | Data | 98 B | — |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-2500/training_state.json | Data | 98 B | — |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-3000/training_state.json | Data | 98 B | — |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-3500/training_state.json | Data | 98 B | — |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-4000/training_state.json | Data | 98 B | — |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-500/training_state.json | Data | 96 B | — |
| legacy/llama32/exp4_gated_loadbalancing_seed1/final_model/training_state.json | Data | 98 B | — |
| legacy/llama32/exp4_gated_loadbalancing_seed1/final_results.json | Data | 260 B | — |
| legacy/llama32/exp4_gated_loadbalancing_seed1/visualizations/exp4_gated_loadbalancing_seed1_analysis.json | Data | 6.7 KB | — |
| legacy/llama32/exp4_gated_loadbalancing_seed2/best_model/training_state.json | Data | 97 B | — |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-1000/training_state.json | Data | 98 B | — |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-1500/training_state.json | Data | 98 B | — |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-2000/training_state.json | Data | 98 B | — |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-2500/training_state.json | Data | 98 B | — |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-3000/training_state.json | Data | 98 B | — |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-3500/training_state.json | Data | 98 B | — |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-4000/training_state.json | Data | 98 B | — |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-500/training_state.json | Data | 97 B | — |
| legacy/llama32/exp4_gated_loadbalancing_seed2/final_model/training_state.json | Data | 98 B | — |
| legacy/llama32/exp4_gated_loadbalancing_seed2/final_results.json | Data | 263 B | — |
| legacy/llama32/exp4_gated_loadbalancing_seed2/visualizations/exp4_gated_loadbalancing_seed2_analysis.json | Data | 6.7 KB | — |
| legacy/llama32/exp4_gated_loadbalancing_seed3/best_model/training_state.json | Data | 97 B | — |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-1000/training_state.json | Data | 98 B | — |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-1500/training_state.json | Data | 98 B | — |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-2000/training_state.json | Data | 98 B | — |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-2500/training_state.json | Data | 98 B | — |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-3000/training_state.json | Data | 98 B | — |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-3500/training_state.json | Data | 98 B | — |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-4000/training_state.json | Data | 98 B | — |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-500/training_state.json | Data | 96 B | — |
| legacy/llama32/exp4_gated_loadbalancing_seed3/final_model/training_state.json | Data | 98 B | — |
| legacy/llama32/exp4_gated_loadbalancing_seed3/final_results.json | Data | 262 B | — |
| legacy/llama32/exp4_gated_loadbalancing_seed3/visualizations/exp4_gated_loadbalancing_seed3_analysis.json | Data | 6.7 KB | — |
| legacy/llama32/exp5_gated_topk_seed1/best_model/training_state.json | Data | 97 B | — |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-1000/training_state.json | Data | 98 B | — |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-1500/training_state.json | Data | 98 B | — |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-2000/training_state.json | Data | 98 B | — |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-2500/training_state.json | Data | 98 B | — |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-3000/training_state.json | Data | 98 B | — |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-3500/training_state.json | Data | 98 B | — |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-4000/training_state.json | Data | 98 B | — |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-500/training_state.json | Data | 97 B | — |
| legacy/llama32/exp5_gated_topk_seed1/final_model/training_state.json | Data | 98 B | — |
| legacy/llama32/exp5_gated_topk_seed1/final_results.json | Data | 263 B | — |
| legacy/llama32/exp5_gated_topk_seed1/visualizations/exp5_gated_topk_seed1_analysis.json | Data | 6.7 KB | — |
| legacy/llama32/exp5_gated_topk_seed2/best_model/training_state.json | Data | 97 B | — |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-1000/training_state.json | Data | 98 B | — |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-1500/training_state.json | Data | 98 B | — |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-2000/training_state.json | Data | 98 B | — |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-2500/training_state.json | Data | 98 B | — |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-3000/training_state.json | Data | 98 B | — |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-3500/training_state.json | Data | 98 B | — |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-4000/training_state.json | Data | 98 B | — |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-500/training_state.json | Data | 97 B | — |
| legacy/llama32/exp5_gated_topk_seed2/final_model/training_state.json | Data | 98 B | — |
| legacy/llama32/exp5_gated_topk_seed2/final_results.json | Data | 263 B | — |
| legacy/llama32/exp5_gated_topk_seed2/visualizations/exp5_gated_topk_seed2_analysis.json | Data | 6.7 KB | — |
| legacy/llama32/exp5_gated_topk_seed3/best_model/training_state.json | Data | 97 B | — |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-1000/training_state.json | Data | 98 B | — |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-1500/training_state.json | Data | 98 B | — |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-2000/training_state.json | Data | 98 B | — |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-2500/training_state.json | Data | 98 B | — |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-3000/training_state.json | Data | 98 B | — |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-3500/training_state.json | Data | 98 B | — |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-4000/training_state.json | Data | 98 B | — |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-500/training_state.json | Data | 97 B | — |
| legacy/llama32/exp5_gated_topk_seed3/final_model/training_state.json | Data | 98 B | — |
| legacy/llama32/exp5_gated_topk_seed3/final_results.json | Data | 262 B | — |
| legacy/llama32/exp5_gated_topk_seed3/visualizations/exp5_gated_topk_seed3_analysis.json | Data | 6.7 KB | — |
| legacy/llama32_modified/ablation_partial_gating_seed1/best_model/training_state.json | Data | 199 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-1000/training_state.json | Data | 196 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-1500/training_state.json | Data | 197 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-2000/training_state.json | Data | 198 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-2500/training_state.json | Data | 199 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-3000/training_state.json | Data | 199 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-3500/training_state.json | Data | 198 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-4000/training_state.json | Data | 198 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-500/training_state.json | Data | 196 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed1/epoch-1/training_state.json | Data | 193 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed1/epoch-2/training_state.json | Data | 195 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed1/epoch-3/training_state.json | Data | 196 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed1/epoch-4/training_state.json | Data | 195 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed1/final_model/training_state.json | Data | 195 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed1/final_results.json | Data | 289 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed1/latest/training_state.json | Data | 195 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed1/visualizations/ablation_partial_gating_seed1_analysis.json | Data | 5.6 KB | — |
| legacy/llama32_modified/ablation_partial_gating_seed2/best_model/training_state.json | Data | 198 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-1000/training_state.json | Data | 194 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-1500/training_state.json | Data | 194 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-2000/training_state.json | Data | 198 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-2500/training_state.json | Data | 199 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-3000/training_state.json | Data | 199 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-3500/training_state.json | Data | 199 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-4000/training_state.json | Data | 199 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-500/training_state.json | Data | 197 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed2/epoch-1/training_state.json | Data | 191 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed2/epoch-2/training_state.json | Data | 195 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed2/epoch-3/training_state.json | Data | 196 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed2/epoch-4/training_state.json | Data | 196 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed2/final_model/training_state.json | Data | 196 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed2/final_results.json | Data | 287 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed2/latest/training_state.json | Data | 196 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed2/visualizations/ablation_partial_gating_seed2_analysis.json | Data | 5.6 KB | — |
| legacy/llama32_modified/ablation_partial_gating_seed3/best_model/training_state.json | Data | 198 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-1000/training_state.json | Data | 194 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-1500/training_state.json | Data | 196 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-2000/training_state.json | Data | 198 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-2500/training_state.json | Data | 199 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-3000/training_state.json | Data | 198 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-3500/training_state.json | Data | 199 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-4000/training_state.json | Data | 198 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-500/training_state.json | Data | 197 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed3/epoch-1/training_state.json | Data | 193 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed3/epoch-2/training_state.json | Data | 195 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed3/epoch-3/training_state.json | Data | 196 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed3/epoch-4/training_state.json | Data | 196 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed3/final_model/training_state.json | Data | 196 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed3/final_results.json | Data | 289 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed3/latest/training_state.json | Data | 195 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed3/visualizations/ablation_partial_gating_seed3_analysis.json | Data | 5.7 KB | — |
| legacy/llama32_modified/exp2_gated_2experts_seed1/best_model/training_state.json | Data | 198 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-1000/training_state.json | Data | 197 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-1500/training_state.json | Data | 197 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-2000/training_state.json | Data | 199 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-2500/training_state.json | Data | 199 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-3000/training_state.json | Data | 199 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-3500/training_state.json | Data | 199 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-4000/training_state.json | Data | 199 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-500/training_state.json | Data | 196 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed1/epoch-1/training_state.json | Data | 193 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed1/epoch-2/training_state.json | Data | 196 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed1/epoch-3/training_state.json | Data | 196 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed1/epoch-4/training_state.json | Data | 196 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed1/final_model/training_state.json | Data | 196 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed1/final_results.json | Data | 287 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed1/latest/training_state.json | Data | 198 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed1/visualizations/exp2_gated_2experts_seed1_analysis.json | Data | 5.1 KB | — |
| legacy/llama32_modified/exp2_gated_2experts_seed2/best_model/training_state.json | Data | 197 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-1000/training_state.json | Data | 197 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-1500/training_state.json | Data | 197 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-2000/training_state.json | Data | 198 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-2500/training_state.json | Data | 198 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-3000/training_state.json | Data | 197 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-3500/training_state.json | Data | 198 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-4000/training_state.json | Data | 197 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-500/training_state.json | Data | 197 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed2/epoch-1/training_state.json | Data | 194 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed2/epoch-2/training_state.json | Data | 193 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed2/epoch-3/training_state.json | Data | 195 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed2/epoch-4/training_state.json | Data | 195 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed2/final_model/training_state.json | Data | 195 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed2/final_results.json | Data | 288 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed2/latest/training_state.json | Data | 197 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed2/visualizations/exp2_gated_2experts_seed2_analysis.json | Data | 5.1 KB | — |
| legacy/llama32_modified/exp2_gated_2experts_seed3/best_model/training_state.json | Data | 198 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-1000/training_state.json | Data | 197 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-1500/training_state.json | Data | 197 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-2000/training_state.json | Data | 199 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-2500/training_state.json | Data | 199 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-3000/training_state.json | Data | 199 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-3500/training_state.json | Data | 198 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-4000/training_state.json | Data | 199 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-500/training_state.json | Data | 196 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed3/epoch-1/training_state.json | Data | 194 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed3/epoch-2/training_state.json | Data | 195 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed3/epoch-3/training_state.json | Data | 196 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed3/epoch-4/training_state.json | Data | 195 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed3/final_model/training_state.json | Data | 195 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed3/final_results.json | Data | 289 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed3/latest/training_state.json | Data | 198 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed3/visualizations/exp2_gated_2experts_seed3_analysis.json | Data | 5.2 KB | — |
| legacy/llama32_modified/exp3_gated_3experts_seed1/best_model/training_state.json | Data | 196 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-1000/training_state.json | Data | 197 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-1500/training_state.json | Data | 195 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-2000/training_state.json | Data | 196 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-2500/training_state.json | Data | 198 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-3000/training_state.json | Data | 197 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-3500/training_state.json | Data | 198 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-4000/training_state.json | Data | 198 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-500/training_state.json | Data | 196 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed1/epoch-1/training_state.json | Data | 194 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed1/epoch-2/training_state.json | Data | 195 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed1/epoch-3/training_state.json | Data | 195 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed1/epoch-4/training_state.json | Data | 193 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed1/final_model/training_state.json | Data | 193 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed1/final_results.json | Data | 284 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed1/latest/training_state.json | Data | 198 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed1/visualizations/exp3_gated_3experts_seed1_analysis.json | Data | 6.7 KB | — |
| legacy/llama32_modified/exp3_gated_3experts_seed2/best_model/training_state.json | Data | 199 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-1000/training_state.json | Data | 197 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-1500/training_state.json | Data | 197 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-2000/training_state.json | Data | 198 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-2500/training_state.json | Data | 199 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-3000/training_state.json | Data | 199 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-3500/training_state.json | Data | 199 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-4000/training_state.json | Data | 199 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-500/training_state.json | Data | 196 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed2/epoch-1/training_state.json | Data | 195 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed2/epoch-2/training_state.json | Data | 196 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed2/epoch-3/training_state.json | Data | 196 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed2/epoch-4/training_state.json | Data | 195 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed2/final_model/training_state.json | Data | 195 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed2/final_results.json | Data | 288 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed2/latest/training_state.json | Data | 198 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed2/visualizations/exp3_gated_3experts_seed2_analysis.json | Data | 6.7 KB | — |
| legacy/llama32_modified/exp3_gated_3experts_seed3/best_model/training_state.json | Data | 198 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-1000/training_state.json | Data | 196 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-1500/training_state.json | Data | 196 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-2000/training_state.json | Data | 198 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-2500/training_state.json | Data | 199 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-3000/training_state.json | Data | 197 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-3500/training_state.json | Data | 199 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-4000/training_state.json | Data | 199 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-500/training_state.json | Data | 197 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed3/epoch-1/training_state.json | Data | 193 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed3/epoch-2/training_state.json | Data | 196 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed3/epoch-3/training_state.json | Data | 196 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed3/epoch-4/training_state.json | Data | 196 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed3/final_model/training_state.json | Data | 196 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed3/final_results.json | Data | 288 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed3/latest/training_state.json | Data | 199 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed3/visualizations/exp3_gated_3experts_seed3_analysis.json | Data | 6.7 KB | — |
| legacy/phi2_ablations/ablation_no_l1/best_model/training_state.json | Data | 98 B | — |
| legacy/phi2_ablations/ablation_no_l1/checkpoint-1000/training_state.json | Data | 96 B | — |
| legacy/phi2_ablations/ablation_no_l1/checkpoint-1500/training_state.json | Data | 98 B | — |
| legacy/phi2_ablations/ablation_no_l1/checkpoint-2000/training_state.json | Data | 98 B | — |
| legacy/phi2_ablations/ablation_no_l1/checkpoint-2500/training_state.json | Data | 98 B | — |
| legacy/phi2_ablations/ablation_no_l1/checkpoint-500/training_state.json | Data | 97 B | — |
| legacy/phi2_ablations/ablation_no_l1/final_model/training_state.json | Data | 98 B | — |
| legacy/phi2_ablations/ablation_no_l1/final_results.json | Data | 263 B | — |
| legacy/phi2_ablations/ablation_no_l1/routing_analysis_v2/ablation_no_l1_analysis.json | Data | 18.7 KB | — |
| legacy/phi2_ablations/ablation_no_l1/routing_analysis_v2/ablation_no_l1_routing_analysis.json | Data | 18.9 KB | — |
| legacy/phi2_ablations/ablation_no_l1/visualizations/ablation_no_l1_analysis.json | Data | 7.6 KB | — |
| legacy/phi2_ablations/ablation_no_layer_emb/best_model/training_state.json | Data | 98 B | — |
| legacy/phi2_ablations/ablation_no_layer_emb/checkpoint-1000/training_state.json | Data | 98 B | — |
| legacy/phi2_ablations/ablation_no_layer_emb/checkpoint-1500/training_state.json | Data | 98 B | — |
| legacy/phi2_ablations/ablation_no_layer_emb/checkpoint-2000/training_state.json | Data | 98 B | — |
| legacy/phi2_ablations/ablation_no_layer_emb/checkpoint-2500/training_state.json | Data | 98 B | — |
| legacy/phi2_ablations/ablation_no_layer_emb/checkpoint-500/training_state.json | Data | 97 B | — |
| legacy/phi2_ablations/ablation_no_layer_emb/final_model/training_state.json | Data | 98 B | — |
| legacy/phi2_ablations/ablation_no_layer_emb/final_results.json | Data | 263 B | — |
| legacy/phi2_ablations/ablation_no_layer_emb/routing_analysis_v2/ablation_no_layer_emb_analysis.json | Data | 18.7 KB | — |
| legacy/phi2_ablations/ablation_no_layer_emb/routing_analysis_v2/ablation_no_layer_emb_routing_analysis.json | Data | 18.9 KB | — |
| legacy/phi2_ablations/ablation_no_layer_emb/visualizations/ablation_no_layer_emb_analysis.json | Data | 7.6 KB | — |
| legacy/phi2_ablations/ablation_partial_gating/best_model/training_state.json | Data | 98 B | — |
| legacy/phi2_ablations/ablation_partial_gating/checkpoint-1000/training_state.json | Data | 98 B | — |
| legacy/phi2_ablations/ablation_partial_gating/checkpoint-1500/training_state.json | Data | 98 B | — |
| legacy/phi2_ablations/ablation_partial_gating/checkpoint-2000/training_state.json | Data | 98 B | — |
| legacy/phi2_ablations/ablation_partial_gating/checkpoint-2500/training_state.json | Data | 98 B | — |
| legacy/phi2_ablations/ablation_partial_gating/checkpoint-500/training_state.json | Data | 97 B | — |
| legacy/phi2_ablations/ablation_partial_gating/final_model/training_state.json | Data | 98 B | — |
| legacy/phi2_ablations/ablation_partial_gating/routing_analysis_v2/ablation_partial_gating_analysis.json | Data | 18.7 KB | — |
| legacy/phi2_ablations/ablation_partial_gating/routing_analysis_v2/ablation_partial_gating_routing_analysis.json | Data | 19.0 KB | — |
| legacy/pythia410m/ablation_no_l1_seed1/best_model/training_state.json | Data | 97 B | — |
| legacy/pythia410m/ablation_no_l1_seed1/checkpoint-1000/training_state.json | Data | 96 B | — |
| legacy/pythia410m/ablation_no_l1_seed1/checkpoint-1500/training_state.json | Data | 97 B | — |
| legacy/pythia410m/ablation_no_l1_seed1/checkpoint-2000/training_state.json | Data | 97 B | — |
| legacy/pythia410m/ablation_no_l1_seed1/checkpoint-500/training_state.json | Data | 97 B | — |
| legacy/pythia410m/ablation_no_l1_seed2/best_model/training_state.json | Data | 98 B | — |
| legacy/pythia410m/ablation_no_l1_seed2/checkpoint-1000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/ablation_no_l1_seed2/checkpoint-1500/training_state.json | Data | 98 B | — |
| legacy/pythia410m/ablation_no_l1_seed2/checkpoint-2000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/ablation_no_l1_seed2/checkpoint-500/training_state.json | Data | 97 B | — |
| legacy/pythia410m/ablation_no_l1_seed3/best_model/training_state.json | Data | 98 B | — |
| legacy/pythia410m/ablation_no_l1_seed3/checkpoint-1000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/ablation_no_l1_seed3/checkpoint-1500/training_state.json | Data | 98 B | — |
| legacy/pythia410m/ablation_no_l1_seed3/checkpoint-2000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/ablation_no_l1_seed3/checkpoint-500/training_state.json | Data | 97 B | — |
| legacy/pythia410m/ablation_no_layer_emb_seed1/best_model/training_state.json | Data | 97 B | — |
| legacy/pythia410m/ablation_no_layer_emb_seed1/checkpoint-1000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/ablation_no_layer_emb_seed1/checkpoint-1500/training_state.json | Data | 97 B | — |
| legacy/pythia410m/ablation_no_layer_emb_seed1/checkpoint-2000/training_state.json | Data | 97 B | — |
| legacy/pythia410m/ablation_no_layer_emb_seed1/checkpoint-500/training_state.json | Data | 96 B | — |
| legacy/pythia410m/ablation_no_layer_emb_seed2/best_model/training_state.json | Data | 98 B | — |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-1000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-1500/training_state.json | Data | 98 B | — |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-2000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-2500/training_state.json | Data | 98 B | — |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-3000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-3500/training_state.json | Data | 98 B | — |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-4000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-500/training_state.json | Data | 97 B | — |
| legacy/pythia410m/ablation_no_layer_emb_seed3/best_model/training_state.json | Data | 96 B | — |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-1000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-1500/training_state.json | Data | 98 B | — |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-2000/training_state.json | Data | 96 B | — |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-2500/training_state.json | Data | 96 B | — |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-3000/training_state.json | Data | 96 B | — |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-3500/training_state.json | Data | 96 B | — |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-4000/training_state.json | Data | 96 B | — |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-500/training_state.json | Data | 97 B | — |
| legacy/pythia410m/ablation_partial_gating_seed1/best_model/training_state.json | Data | 98 B | — |
| legacy/pythia410m/ablation_partial_gating_seed1/checkpoint-1000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/ablation_partial_gating_seed1/checkpoint-1500/training_state.json | Data | 98 B | — |
| legacy/pythia410m/ablation_partial_gating_seed1/checkpoint-2000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/ablation_partial_gating_seed1/checkpoint-500/training_state.json | Data | 97 B | — |
| legacy/pythia410m/ablation_partial_gating_seed2/best_model/training_state.json | Data | 98 B | — |
| legacy/pythia410m/ablation_partial_gating_seed2/checkpoint-1000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/ablation_partial_gating_seed2/checkpoint-1500/training_state.json | Data | 98 B | — |
| legacy/pythia410m/ablation_partial_gating_seed2/checkpoint-2000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/ablation_partial_gating_seed2/checkpoint-500/training_state.json | Data | 97 B | — |
| legacy/pythia410m/ablation_partial_gating_seed3/best_model/training_state.json | Data | 98 B | — |
| legacy/pythia410m/ablation_partial_gating_seed3/checkpoint-1000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/ablation_partial_gating_seed3/checkpoint-1500/training_state.json | Data | 98 B | — |
| legacy/pythia410m/ablation_partial_gating_seed3/checkpoint-2000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/ablation_partial_gating_seed3/checkpoint-500/training_state.json | Data | 97 B | — |
| legacy/pythia410m/exp2_gated_2experts_seed1/best_model/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-1000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-1500/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-2000/training_state.json | Data | 97 B | — |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-2500/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-3000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-3500/training_state.json | Data | 97 B | — |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-4000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-500/training_state.json | Data | 97 B | — |
| legacy/pythia410m/exp2_gated_2experts_seed1/final_model/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp2_gated_2experts_seed1/final_results.json | Data | 263 B | — |
| legacy/pythia410m/exp2_gated_2experts_seed1/visualizations/exp2_gated_2experts_seed1_analysis.json | Data | 4.5 KB | — |
| legacy/pythia410m/exp2_gated_2experts_seed2/best_model/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-1000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-1500/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-2000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-2500/training_state.json | Data | 97 B | — |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-3000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-3500/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-4000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-500/training_state.json | Data | 97 B | — |
| legacy/pythia410m/exp2_gated_2experts_seed2/final_model/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp2_gated_2experts_seed2/final_results.json | Data | 263 B | — |
| legacy/pythia410m/exp2_gated_2experts_seed2/visualizations/exp2_gated_2experts_seed2_analysis.json | Data | 4.5 KB | — |
| legacy/pythia410m/exp2_gated_2experts_seed3/best_model/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-1000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-1500/training_state.json | Data | 97 B | — |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-2000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-2500/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-3000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-3500/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-4000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-500/training_state.json | Data | 97 B | — |
| legacy/pythia410m/exp2_gated_2experts_seed3/final_model/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp2_gated_2experts_seed3/final_results.json | Data | 263 B | — |
| legacy/pythia410m/exp2_gated_2experts_seed3/visualizations/exp2_gated_2experts_seed3_analysis.json | Data | 4.5 KB | — |
| legacy/pythia410m/exp3_gated_3experts_seed1/best_model/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-1000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-1500/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-2000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-2500/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-3000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-3500/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-4000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-500/training_state.json | Data | 97 B | — |
| legacy/pythia410m/exp3_gated_3experts_seed1/final_model/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp3_gated_3experts_seed1/final_results.json | Data | 262 B | — |
| legacy/pythia410m/exp3_gated_3experts_seed1/visualizations/exp3_gated_3experts_seed1_analysis.json | Data | 5.8 KB | — |
| legacy/pythia410m/exp3_gated_3experts_seed2/best_model/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-1000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-1500/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-2000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-2500/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-3000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-3500/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-4000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-500/training_state.json | Data | 97 B | — |
| legacy/pythia410m/exp3_gated_3experts_seed2/final_model/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp3_gated_3experts_seed2/final_results.json | Data | 261 B | — |
| legacy/pythia410m/exp3_gated_3experts_seed2/visualizations/exp3_gated_3experts_seed2_analysis.json | Data | 5.8 KB | — |
| legacy/pythia410m/exp3_gated_3experts_seed3/best_model/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-1000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-1500/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-2000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-2500/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-3000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-3500/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-4000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-500/training_state.json | Data | 97 B | — |
| legacy/pythia410m/exp3_gated_3experts_seed3/final_model/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp3_gated_3experts_seed3/final_results.json | Data | 262 B | — |
| legacy/pythia410m/exp3_gated_3experts_seed3/visualizations/exp3_gated_3experts_seed3_analysis.json | Data | 5.8 KB | — |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/best_model/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-1000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-1500/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-2000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-2500/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-3000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-3500/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-4000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-500/training_state.json | Data | 97 B | — |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/final_model/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/final_results.json | Data | 262 B | — |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/visualizations/exp4_gated_loadbalancing_seed1_analysis.json | Data | 5.9 KB | — |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/best_model/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-1000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-1500/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-2000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-2500/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-3000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-3500/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-4000/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-500/training_state.json | Data | 97 B | — |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/final_model/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/final_results.json | Data | 262 B | — |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/visualizations/exp4_gated_loadbalancing_seed2_analysis.json | Data | 5.8 KB | — |
| legacy/pythia410m/exp4_gated_loadbalancing_seed3/best_model/training_state.json | Data | 98 B | — |
| legacy/pythia410m/exp4_gated_loadbalancing_seed3/checkpoint-1000/training_state.json | Data | 98 B | — |
| README.md | Documentation | 659 B | — |
| legacy/gemma2/exp2_gated_2experts_seed1/best_model/expert_pools.pt | Other | 19.4 MB | c8225b311e05 |
| legacy/gemma2/exp2_gated_2experts_seed1/best_model/gated_lora_config.pt | Other | 1.8 KB | d74c5d7b3d63 |
| legacy/gemma2/exp2_gated_2experts_seed1/best_model/gating_network.pt | Other | 33.9 MB | 9dbf7da061dd |
| legacy/gemma2/exp2_gated_2experts_seed1/best_model/scheduler.pt | Other | 1.7 KB | 3e43ae9e84c6 |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-1000/expert_pools.pt | Other | 19.4 MB | 379603235f81 |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | d74c5d7b3d63 |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-1000/gating_network.pt | Other | 33.9 MB | e72903bd891a |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 75d0483a00c8 |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-1500/expert_pools.pt | Other | 19.4 MB | 296479a9750b |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | d74c5d7b3d63 |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-1500/gating_network.pt | Other | 33.9 MB | 5ec9930a382c |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-1500/scheduler.pt | Other | 1.7 KB | a930f4a734fe |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-2000/expert_pools.pt | Other | 19.4 MB | 8dabf2556b26 |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | d74c5d7b3d63 |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-2000/gating_network.pt | Other | 33.9 MB | c2368179472e |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-2000/scheduler.pt | Other | 1.7 KB | b5ded2205a43 |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-2500/expert_pools.pt | Other | 19.4 MB | 66d32ebe3d70 |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | d74c5d7b3d63 |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-2500/gating_network.pt | Other | 33.9 MB | 78a3cc920337 |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 8edb16e6cc0f |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-3000/expert_pools.pt | Other | 19.4 MB | a513320f58af |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | d74c5d7b3d63 |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-3000/gating_network.pt | Other | 33.9 MB | 58e45d7f13f5 |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 438e7c9aba3b |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-3500/expert_pools.pt | Other | 19.4 MB | c780d786b377 |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | d74c5d7b3d63 |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-3500/gating_network.pt | Other | 33.9 MB | 578d88af8a54 |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 82a86129150c |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-4000/expert_pools.pt | Other | 19.4 MB | 1a7b968e4cb5 |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | d74c5d7b3d63 |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-4000/gating_network.pt | Other | 33.9 MB | 6f9fd4968394 |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 9793afb9d64c |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-500/expert_pools.pt | Other | 19.4 MB | 31a02d0aeb43 |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | d74c5d7b3d63 |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-500/gating_network.pt | Other | 33.9 MB | 70850321c37d |
| legacy/gemma2/exp2_gated_2experts_seed1/checkpoint-500/scheduler.pt | Other | 1.7 KB | d2c4f1faa352 |
| legacy/gemma2/exp2_gated_2experts_seed1/final_model/expert_pools.pt | Other | 19.4 MB | a4774d8f2b01 |
| legacy/gemma2/exp2_gated_2experts_seed1/final_model/gated_lora_config.pt | Other | 1.8 KB | d74c5d7b3d63 |
| legacy/gemma2/exp2_gated_2experts_seed1/final_model/gating_network.pt | Other | 33.9 MB | 3108d13f7e4f |
| legacy/gemma2/exp2_gated_2experts_seed1/final_model/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/gemma2/exp2_gated_2experts_seed1/visualizations/exp2_gated_2experts_seed1_entropy_per_layer.png | Other | 43.0 KB | 43455caff5e7 |
| legacy/gemma2/exp2_gated_2experts_seed1/visualizations/exp2_gated_2experts_seed1_layer_expert_heatmap.png | Other | 105.4 KB | 151e016edabb |
| legacy/gemma2/exp2_gated_2experts_seed1/visualizations/exp2_gated_2experts_seed1_task_expert_usage.png | Other | 37.5 KB | 9bc1568d5b47 |
| legacy/gemma2/exp2_gated_2experts_seed1/visualizations/exp2_gated_2experts_seed1_token_routing_1.png | Other | 50.9 KB | 9eff21d16177 |
| legacy/gemma2/exp2_gated_2experts_seed1/visualizations/exp2_gated_2experts_seed1_token_routing_2.png | Other | 50.7 KB | 83599d65d3d0 |
| legacy/gemma2/exp2_gated_2experts_seed1/visualizations/exp2_gated_2experts_seed1_token_routing_3.png | Other | 51.2 KB | bb185f41c6c3 |
| legacy/gemma2/exp2_gated_2experts_seed2/best_model/expert_pools.pt | Other | 19.4 MB | 8a594254b016 |
| legacy/gemma2/exp2_gated_2experts_seed2/best_model/gated_lora_config.pt | Other | 1.8 KB | d74c5d7b3d63 |
| legacy/gemma2/exp2_gated_2experts_seed2/best_model/gating_network.pt | Other | 33.9 MB | bb20c96d88a8 |
| legacy/gemma2/exp2_gated_2experts_seed2/best_model/scheduler.pt | Other | 1.7 KB | 256b90657b80 |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-1000/expert_pools.pt | Other | 19.4 MB | 350ed122efab |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | d74c5d7b3d63 |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-1000/gating_network.pt | Other | 33.9 MB | 9aa142c30d0d |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 75d0483a00c8 |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-1500/expert_pools.pt | Other | 19.4 MB | 190073fbf59c |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | d74c5d7b3d63 |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-1500/gating_network.pt | Other | 33.9 MB | a4d6c0b882bd |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-1500/scheduler.pt | Other | 1.7 KB | a930f4a734fe |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-2000/expert_pools.pt | Other | 19.4 MB | 69557b40b81c |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | d74c5d7b3d63 |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-2000/gating_network.pt | Other | 33.9 MB | 6632edd6a2a6 |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-2000/scheduler.pt | Other | 1.7 KB | b5ded2205a43 |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-2500/expert_pools.pt | Other | 19.4 MB | cce5f7cd5082 |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | d74c5d7b3d63 |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-2500/gating_network.pt | Other | 33.9 MB | 4a57b65890da |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 8edb16e6cc0f |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-3000/expert_pools.pt | Other | 19.4 MB | 76484fba7a2a |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | d74c5d7b3d63 |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-3000/gating_network.pt | Other | 33.9 MB | 43b7c4a513bf |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 438e7c9aba3b |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-3500/expert_pools.pt | Other | 19.4 MB | e2f54aa65058 |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | d74c5d7b3d63 |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-3500/gating_network.pt | Other | 33.9 MB | 548add376ee5 |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 82a86129150c |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-4000/expert_pools.pt | Other | 19.4 MB | aec55729c96f |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | d74c5d7b3d63 |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-4000/gating_network.pt | Other | 33.9 MB | 82df6a08e125 |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 9793afb9d64c |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-500/expert_pools.pt | Other | 19.4 MB | daf68467947f |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | d74c5d7b3d63 |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-500/gating_network.pt | Other | 33.9 MB | 40b105217965 |
| legacy/gemma2/exp2_gated_2experts_seed2/checkpoint-500/scheduler.pt | Other | 1.7 KB | d2c4f1faa352 |
| legacy/gemma2/exp2_gated_2experts_seed2/final_model/expert_pools.pt | Other | 19.4 MB | cc7ef50950de |
| legacy/gemma2/exp2_gated_2experts_seed2/final_model/gated_lora_config.pt | Other | 1.8 KB | d74c5d7b3d63 |
| legacy/gemma2/exp2_gated_2experts_seed2/final_model/gating_network.pt | Other | 33.9 MB | 15b9a53d6da0 |
| legacy/gemma2/exp2_gated_2experts_seed2/final_model/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/gemma2/exp2_gated_2experts_seed2/visualizations/exp2_gated_2experts_seed2_entropy_per_layer.png | Other | 43.0 KB | dc1777729c31 |
| legacy/gemma2/exp2_gated_2experts_seed2/visualizations/exp2_gated_2experts_seed2_layer_expert_heatmap.png | Other | 105.8 KB | 10673b1d3338 |
| legacy/gemma2/exp2_gated_2experts_seed2/visualizations/exp2_gated_2experts_seed2_task_expert_usage.png | Other | 37.1 KB | 2ee310ec5e03 |
| legacy/gemma2/exp2_gated_2experts_seed2/visualizations/exp2_gated_2experts_seed2_token_routing_1.png | Other | 44.1 KB | 7f2cd0f95189 |
| legacy/gemma2/exp2_gated_2experts_seed2/visualizations/exp2_gated_2experts_seed2_token_routing_2.png | Other | 44.2 KB | bea32b5b76d8 |
| legacy/gemma2/exp2_gated_2experts_seed2/visualizations/exp2_gated_2experts_seed2_token_routing_3.png | Other | 44.4 KB | d9d2d81d167d |
| legacy/gemma2/exp2_gated_2experts_seed3/best_model/expert_pools.pt | Other | 19.4 MB | 17982a49897c |
| legacy/gemma2/exp2_gated_2experts_seed3/best_model/gated_lora_config.pt | Other | 1.8 KB | d74c5d7b3d63 |
| legacy/gemma2/exp2_gated_2experts_seed3/best_model/gating_network.pt | Other | 33.9 MB | 718defbaf1eb |
| legacy/gemma2/exp2_gated_2experts_seed3/best_model/scheduler.pt | Other | 1.7 KB | 256b90657b80 |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-1000/expert_pools.pt | Other | 19.4 MB | fc93dbcffa81 |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | d74c5d7b3d63 |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-1000/gating_network.pt | Other | 33.9 MB | ec849e725c6e |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 75d0483a00c8 |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-1500/expert_pools.pt | Other | 19.4 MB | 696ec53e8c28 |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | d74c5d7b3d63 |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-1500/gating_network.pt | Other | 33.9 MB | c5a76f0bddeb |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-1500/scheduler.pt | Other | 1.7 KB | a930f4a734fe |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-2000/expert_pools.pt | Other | 19.4 MB | b94317cd68e8 |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | d74c5d7b3d63 |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-2000/gating_network.pt | Other | 33.9 MB | b35028425e84 |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-2000/scheduler.pt | Other | 1.7 KB | b5ded2205a43 |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-2500/expert_pools.pt | Other | 19.4 MB | 5f5691b71813 |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | d74c5d7b3d63 |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-2500/gating_network.pt | Other | 33.9 MB | 179386c524e0 |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 8edb16e6cc0f |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-3000/expert_pools.pt | Other | 19.4 MB | f93a9bf3ee33 |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | d74c5d7b3d63 |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-3000/gating_network.pt | Other | 33.9 MB | bb94bab6e83c |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 438e7c9aba3b |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-3500/expert_pools.pt | Other | 19.4 MB | 2f15f812efd7 |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | d74c5d7b3d63 |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-3500/gating_network.pt | Other | 33.9 MB | 09e03213521c |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 82a86129150c |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-4000/expert_pools.pt | Other | 19.4 MB | 9c7a0957dd93 |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | d74c5d7b3d63 |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-4000/gating_network.pt | Other | 33.9 MB | 952aa8a2efb1 |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 9793afb9d64c |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-500/expert_pools.pt | Other | 19.4 MB | 76e251a856b2 |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | d74c5d7b3d63 |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-500/gating_network.pt | Other | 33.9 MB | 68e0fbf0f1d6 |
| legacy/gemma2/exp2_gated_2experts_seed3/checkpoint-500/scheduler.pt | Other | 1.7 KB | d2c4f1faa352 |
| legacy/gemma2/exp2_gated_2experts_seed3/final_model/expert_pools.pt | Other | 19.4 MB | 37b25deee0d1 |
| legacy/gemma2/exp2_gated_2experts_seed3/final_model/gated_lora_config.pt | Other | 1.8 KB | d74c5d7b3d63 |
| legacy/gemma2/exp2_gated_2experts_seed3/final_model/gating_network.pt | Other | 33.9 MB | fe7bce8555cf |
| legacy/gemma2/exp2_gated_2experts_seed3/final_model/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/gemma2/exp2_gated_2experts_seed3/visualizations/exp2_gated_2experts_seed3_entropy_per_layer.png | Other | 43.7 KB | 83d887b1bf12 |
| legacy/gemma2/exp2_gated_2experts_seed3/visualizations/exp2_gated_2experts_seed3_layer_expert_heatmap.png | Other | 107.5 KB | 9f71112c1dd6 |
| legacy/gemma2/exp2_gated_2experts_seed3/visualizations/exp2_gated_2experts_seed3_task_expert_usage.png | Other | 37.8 KB | 8587e0dd600b |
| legacy/gemma2/exp2_gated_2experts_seed3/visualizations/exp2_gated_2experts_seed3_token_routing_1.png | Other | 46.0 KB | 3e2bd46d1783 |
| legacy/gemma2/exp2_gated_2experts_seed3/visualizations/exp2_gated_2experts_seed3_token_routing_2.png | Other | 45.8 KB | 5ce8e01af9b6 |
| legacy/gemma2/exp2_gated_2experts_seed3/visualizations/exp2_gated_2experts_seed3_token_routing_3.png | Other | 46.1 KB | eee819613b1d |
| legacy/gemma2/exp3_gated_3experts_seed1/best_model/expert_pools.pt | Other | 45.0 MB | 83ec11fe6da4 |
| legacy/gemma2/exp3_gated_3experts_seed1/best_model/gated_lora_config.pt | Other | 1.8 KB | 3a0ff4effb43 |
| legacy/gemma2/exp3_gated_3experts_seed1/best_model/gating_network.pt | Other | 33.9 MB | a3e5a7e423db |
| legacy/gemma2/exp3_gated_3experts_seed1/best_model/scheduler.pt | Other | 1.7 KB | 039753c3afc8 |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-1000/expert_pools.pt | Other | 45.0 MB | be2881321abe |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | 3a0ff4effb43 |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-1000/gating_network.pt | Other | 33.9 MB | 0d0f6ad0fc40 |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 75d0483a00c8 |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-1500/expert_pools.pt | Other | 45.0 MB | 1f76f6a78b1f |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | 3a0ff4effb43 |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-1500/gating_network.pt | Other | 33.9 MB | 45dc63a3e051 |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-1500/scheduler.pt | Other | 1.7 KB | a930f4a734fe |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-2000/expert_pools.pt | Other | 45.0 MB | e9f68d506330 |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | 3a0ff4effb43 |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-2000/gating_network.pt | Other | 33.9 MB | 00c20bbd5fe2 |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-2000/scheduler.pt | Other | 1.7 KB | b5ded2205a43 |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-2500/expert_pools.pt | Other | 45.0 MB | 3dfd54af0180 |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | 3a0ff4effb43 |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-2500/gating_network.pt | Other | 33.9 MB | 967c304b9290 |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 8edb16e6cc0f |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-3000/expert_pools.pt | Other | 45.0 MB | fb68ff27f2d5 |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | 3a0ff4effb43 |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-3000/gating_network.pt | Other | 33.9 MB | b079d3e05904 |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 438e7c9aba3b |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-3500/expert_pools.pt | Other | 45.0 MB | 3988b2c21cdd |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | 3a0ff4effb43 |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-3500/gating_network.pt | Other | 33.9 MB | 4cf8b87785fa |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 82a86129150c |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-4000/expert_pools.pt | Other | 45.0 MB | b45c1070268c |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | 3a0ff4effb43 |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-4000/gating_network.pt | Other | 33.9 MB | bc0a41d7f0f1 |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 9793afb9d64c |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-500/expert_pools.pt | Other | 45.0 MB | 46becb6e4814 |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | 3a0ff4effb43 |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-500/gating_network.pt | Other | 33.9 MB | ed05a438ac13 |
| legacy/gemma2/exp3_gated_3experts_seed1/checkpoint-500/scheduler.pt | Other | 1.7 KB | d2c4f1faa352 |
| legacy/gemma2/exp3_gated_3experts_seed1/final_model/expert_pools.pt | Other | 45.0 MB | fd33930e1d37 |
| legacy/gemma2/exp3_gated_3experts_seed1/final_model/gated_lora_config.pt | Other | 1.8 KB | 3a0ff4effb43 |
| legacy/gemma2/exp3_gated_3experts_seed1/final_model/gating_network.pt | Other | 33.9 MB | 415ac81a66b5 |
| legacy/gemma2/exp3_gated_3experts_seed1/final_model/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/gemma2/exp3_gated_3experts_seed1/visualizations/exp3_gated_3experts_seed1_entropy_per_layer.png | Other | 42.3 KB | 613803b67a87 |
| legacy/gemma2/exp3_gated_3experts_seed1/visualizations/exp3_gated_3experts_seed1_layer_expert_heatmap.png | Other | 103.5 KB | 05121e9663b7 |
| legacy/gemma2/exp3_gated_3experts_seed1/visualizations/exp3_gated_3experts_seed1_task_expert_usage.png | Other | 39.1 KB | 6c2ac9350c8f |
| legacy/gemma2/exp3_gated_3experts_seed1/visualizations/exp3_gated_3experts_seed1_token_routing_1.png | Other | 44.9 KB | 1778e94ba9cd |
| legacy/gemma2/exp3_gated_3experts_seed1/visualizations/exp3_gated_3experts_seed1_token_routing_2.png | Other | 45.1 KB | 3cf57304bde0 |
| legacy/gemma2/exp3_gated_3experts_seed1/visualizations/exp3_gated_3experts_seed1_token_routing_3.png | Other | 45.2 KB | be73e2570616 |
| legacy/gemma2/exp3_gated_3experts_seed2/best_model/expert_pools.pt | Other | 45.0 MB | 0c0e174b37e7 |
| legacy/gemma2/exp3_gated_3experts_seed2/best_model/gated_lora_config.pt | Other | 1.8 KB | 3a0ff4effb43 |
| legacy/gemma2/exp3_gated_3experts_seed2/best_model/gating_network.pt | Other | 33.9 MB | 95582465905a |
| legacy/gemma2/exp3_gated_3experts_seed2/best_model/scheduler.pt | Other | 1.7 KB | d2c4f1faa352 |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-1000/expert_pools.pt | Other | 45.0 MB | 4706179d6935 |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | 3a0ff4effb43 |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-1000/gating_network.pt | Other | 33.9 MB | 85069da6714b |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 75d0483a00c8 |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-1500/expert_pools.pt | Other | 45.0 MB | 61860f315931 |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | 3a0ff4effb43 |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-1500/gating_network.pt | Other | 33.9 MB | 08ed058dc295 |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-1500/scheduler.pt | Other | 1.7 KB | a930f4a734fe |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-2000/expert_pools.pt | Other | 45.0 MB | da1c56794594 |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | 3a0ff4effb43 |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-2000/gating_network.pt | Other | 33.9 MB | 76dc7832d840 |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-2000/scheduler.pt | Other | 1.7 KB | b5ded2205a43 |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-2500/expert_pools.pt | Other | 45.0 MB | db08f28f20f5 |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | 3a0ff4effb43 |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-2500/gating_network.pt | Other | 33.9 MB | 362fe626e5af |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 8edb16e6cc0f |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-3000/expert_pools.pt | Other | 45.0 MB | beed35565ef7 |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | 3a0ff4effb43 |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-3000/gating_network.pt | Other | 33.9 MB | c8c2cd971753 |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 438e7c9aba3b |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-3500/expert_pools.pt | Other | 45.0 MB | 12ace0adab19 |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | 3a0ff4effb43 |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-3500/gating_network.pt | Other | 33.9 MB | ace1313803cd |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 82a86129150c |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-4000/expert_pools.pt | Other | 45.0 MB | ee3ffffc9e90 |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | 3a0ff4effb43 |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-4000/gating_network.pt | Other | 33.9 MB | 3e3580def510 |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 9793afb9d64c |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-500/expert_pools.pt | Other | 45.0 MB | 0c0e174b37e7 |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | 3a0ff4effb43 |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-500/gating_network.pt | Other | 33.9 MB | 95582465905a |
| legacy/gemma2/exp3_gated_3experts_seed2/checkpoint-500/scheduler.pt | Other | 1.7 KB | d2c4f1faa352 |
| legacy/gemma2/exp3_gated_3experts_seed2/final_model/expert_pools.pt | Other | 45.0 MB | 74c34bf5b700 |
| legacy/gemma2/exp3_gated_3experts_seed2/final_model/gated_lora_config.pt | Other | 1.8 KB | 3a0ff4effb43 |
| legacy/gemma2/exp3_gated_3experts_seed2/final_model/gating_network.pt | Other | 33.9 MB | 9c99a37662fc |
| legacy/gemma2/exp3_gated_3experts_seed2/final_model/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/gemma2/exp3_gated_3experts_seed2/visualizations/exp3_gated_3experts_seed2_entropy_per_layer.png | Other | 43.0 KB | 63b014f486ed |
| legacy/gemma2/exp3_gated_3experts_seed2/visualizations/exp3_gated_3experts_seed2_layer_expert_heatmap.png | Other | 103.9 KB | 57678a903508 |
| legacy/gemma2/exp3_gated_3experts_seed2/visualizations/exp3_gated_3experts_seed2_task_expert_usage.png | Other | 40.0 KB | ab85cba35854 |
| legacy/gemma2/exp3_gated_3experts_seed2/visualizations/exp3_gated_3experts_seed2_token_routing_1.png | Other | 55.8 KB | 0d711dd0978f |
| legacy/gemma2/exp3_gated_3experts_seed2/visualizations/exp3_gated_3experts_seed2_token_routing_2.png | Other | 55.9 KB | b3a99e06d16c |
| legacy/gemma2/exp3_gated_3experts_seed2/visualizations/exp3_gated_3experts_seed2_token_routing_3.png | Other | 55.7 KB | f5ed5a731c33 |
| legacy/gemma2/exp3_gated_3experts_seed3/best_model/expert_pools.pt | Other | 45.0 MB | 756d2766b157 |
| legacy/gemma2/exp3_gated_3experts_seed3/best_model/gated_lora_config.pt | Other | 1.8 KB | 3a0ff4effb43 |
| legacy/gemma2/exp3_gated_3experts_seed3/best_model/gating_network.pt | Other | 33.9 MB | 680dae923d78 |
| legacy/gemma2/exp3_gated_3experts_seed3/best_model/scheduler.pt | Other | 1.7 KB | 3e43ae9e84c6 |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-1000/expert_pools.pt | Other | 45.0 MB | 8bf9a18cde77 |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | 3a0ff4effb43 |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-1000/gating_network.pt | Other | 33.9 MB | f6aa34133d88 |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 75d0483a00c8 |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-1500/expert_pools.pt | Other | 45.0 MB | f2e62910719a |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | 3a0ff4effb43 |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-1500/gating_network.pt | Other | 33.9 MB | e8827520341a |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-1500/scheduler.pt | Other | 1.7 KB | a930f4a734fe |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-2000/expert_pools.pt | Other | 45.0 MB | a0a931f387ad |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | 3a0ff4effb43 |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-2000/gating_network.pt | Other | 33.9 MB | c23d2a82da0e |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-2000/scheduler.pt | Other | 1.7 KB | b5ded2205a43 |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-2500/expert_pools.pt | Other | 45.0 MB | 31a2627f5a79 |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | 3a0ff4effb43 |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-2500/gating_network.pt | Other | 33.9 MB | 89a469455ffe |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 8edb16e6cc0f |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-3000/expert_pools.pt | Other | 45.0 MB | c39730a93828 |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | 3a0ff4effb43 |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-3000/gating_network.pt | Other | 33.9 MB | f4d72a0118f0 |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 438e7c9aba3b |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-3500/expert_pools.pt | Other | 45.0 MB | 3a5e20844a18 |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | 3a0ff4effb43 |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-3500/gating_network.pt | Other | 33.9 MB | 7abd6d3be134 |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 82a86129150c |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-4000/expert_pools.pt | Other | 45.0 MB | 2a6d0278d9f2 |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | 3a0ff4effb43 |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-4000/gating_network.pt | Other | 33.9 MB | 3cebb27bee1f |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 9793afb9d64c |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-500/expert_pools.pt | Other | 45.0 MB | c3b35878ed64 |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | 3a0ff4effb43 |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-500/gating_network.pt | Other | 33.9 MB | 697972b962ef |
| legacy/gemma2/exp3_gated_3experts_seed3/checkpoint-500/scheduler.pt | Other | 1.7 KB | d2c4f1faa352 |
| legacy/gemma2/exp3_gated_3experts_seed3/final_model/expert_pools.pt | Other | 45.0 MB | 7b7b61329f74 |
| legacy/gemma2/exp3_gated_3experts_seed3/final_model/gated_lora_config.pt | Other | 1.8 KB | 3a0ff4effb43 |
| legacy/gemma2/exp3_gated_3experts_seed3/final_model/gating_network.pt | Other | 33.9 MB | 7fba6f7f268c |
| legacy/gemma2/exp3_gated_3experts_seed3/final_model/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/gemma2/exp3_gated_3experts_seed3/visualizations/exp3_gated_3experts_seed3_entropy_per_layer.png | Other | 43.0 KB | f0cbf4fafb8f |
| legacy/gemma2/exp3_gated_3experts_seed3/visualizations/exp3_gated_3experts_seed3_layer_expert_heatmap.png | Other | 103.7 KB | 6de30d7d0ae9 |
| legacy/gemma2/exp3_gated_3experts_seed3/visualizations/exp3_gated_3experts_seed3_task_expert_usage.png | Other | 38.4 KB | 3fe801bd0bd7 |
| legacy/gemma2/exp3_gated_3experts_seed3/visualizations/exp3_gated_3experts_seed3_token_routing_1.png | Other | 48.7 KB | 5767724aba31 |
| legacy/gemma2/exp3_gated_3experts_seed3/visualizations/exp3_gated_3experts_seed3_token_routing_2.png | Other | 49.0 KB | feff1a08848c |
| legacy/gemma2/exp3_gated_3experts_seed3/visualizations/exp3_gated_3experts_seed3_token_routing_3.png | Other | 49.1 KB | 43e34bb5038f |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/best_model/expert_pools.pt | Other | 45.0 MB | ee9660798a08 |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/best_model/gated_lora_config.pt | Other | 1.8 KB | 3bce6fb9623b |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/best_model/gating_network.pt | Other | 33.9 MB | 1dcaebd4313b |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/best_model/scheduler.pt | Other | 1.7 KB | 039753c3afc8 |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-1000/expert_pools.pt | Other | 45.0 MB | e536b81523a5 |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | 3bce6fb9623b |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-1000/gating_network.pt | Other | 33.9 MB | e11b4f8eab0f |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 75d0483a00c8 |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-1500/expert_pools.pt | Other | 45.0 MB | af4796080908 |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | 3bce6fb9623b |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-1500/gating_network.pt | Other | 33.9 MB | 035417ef4bce |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-1500/scheduler.pt | Other | 1.7 KB | a930f4a734fe |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-2000/expert_pools.pt | Other | 45.0 MB | a1cbc131dcf7 |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | 3bce6fb9623b |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-2000/gating_network.pt | Other | 33.9 MB | 4288993569ae |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-2000/scheduler.pt | Other | 1.7 KB | b5ded2205a43 |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-2500/expert_pools.pt | Other | 45.0 MB | fa065deceaee |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | 3bce6fb9623b |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-2500/gating_network.pt | Other | 33.9 MB | 8506ada37088 |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 8edb16e6cc0f |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-3000/expert_pools.pt | Other | 45.0 MB | bee8e02d2843 |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | 3bce6fb9623b |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-3000/gating_network.pt | Other | 33.9 MB | 83a7ce133071 |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 438e7c9aba3b |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-3500/expert_pools.pt | Other | 45.0 MB | f3f2836cd12d |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | 3bce6fb9623b |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-3500/gating_network.pt | Other | 33.9 MB | 226296080d7d |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 82a86129150c |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-4000/expert_pools.pt | Other | 45.0 MB | b7de8e130ee3 |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | 3bce6fb9623b |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-4000/gating_network.pt | Other | 33.9 MB | a02221ffb368 |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 9793afb9d64c |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-500/expert_pools.pt | Other | 45.0 MB | d24ea0a6f423 |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | 3bce6fb9623b |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-500/gating_network.pt | Other | 33.9 MB | 64969f0e74ba |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/checkpoint-500/scheduler.pt | Other | 1.7 KB | d2c4f1faa352 |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/final_model/expert_pools.pt | Other | 45.0 MB | 996399d7e860 |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/final_model/gated_lora_config.pt | Other | 1.8 KB | 3bce6fb9623b |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/final_model/gating_network.pt | Other | 33.9 MB | 14f19cbc0eac |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/final_model/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/visualizations/exp4_gated_loadbalancing_seed1_entropy_per_layer.png | Other | 43.1 KB | 0b60733fb83b |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/visualizations/exp4_gated_loadbalancing_seed1_layer_expert_heatmap.png | Other | 105.2 KB | f9f25be06873 |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/visualizations/exp4_gated_loadbalancing_seed1_task_expert_usage.png | Other | 44.1 KB | 92006afc6203 |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/visualizations/exp4_gated_loadbalancing_seed1_token_routing_1.png | Other | 53.8 KB | 5b50c1884d88 |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/visualizations/exp4_gated_loadbalancing_seed1_token_routing_2.png | Other | 54.1 KB | 148defb8dec3 |
| legacy/gemma2/exp4_gated_loadbalancing_seed1/visualizations/exp4_gated_loadbalancing_seed1_token_routing_3.png | Other | 54.2 KB | 4e5b2f847089 |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/best_model/expert_pools.pt | Other | 45.0 MB | 739bc7f5d4b6 |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/best_model/gated_lora_config.pt | Other | 1.8 KB | 3bce6fb9623b |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/best_model/gating_network.pt | Other | 33.9 MB | 045e6332b6ab |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/best_model/scheduler.pt | Other | 1.7 KB | d2c4f1faa352 |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-1000/expert_pools.pt | Other | 45.0 MB | 0bd88d6c352c |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | 3bce6fb9623b |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-1000/gating_network.pt | Other | 33.9 MB | 76d9ef30fbc1 |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 75d0483a00c8 |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-1500/expert_pools.pt | Other | 45.0 MB | 2bddffe0b313 |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | 3bce6fb9623b |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-1500/gating_network.pt | Other | 33.9 MB | 10236e050a81 |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-1500/scheduler.pt | Other | 1.7 KB | a930f4a734fe |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-2000/expert_pools.pt | Other | 45.0 MB | 0ff1b29c218a |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | 3bce6fb9623b |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-2000/gating_network.pt | Other | 33.9 MB | afb5daa9ee05 |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-2000/scheduler.pt | Other | 1.7 KB | b5ded2205a43 |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-2500/expert_pools.pt | Other | 45.0 MB | bae3166ef8d3 |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | 3bce6fb9623b |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-2500/gating_network.pt | Other | 33.9 MB | 4898e95c8808 |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 8edb16e6cc0f |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-3000/expert_pools.pt | Other | 45.0 MB | d5d495224f85 |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | 3bce6fb9623b |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-3000/gating_network.pt | Other | 33.9 MB | f4b09592273a |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 438e7c9aba3b |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-3500/expert_pools.pt | Other | 45.0 MB | 0c17eba2c7ee |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | 3bce6fb9623b |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-3500/gating_network.pt | Other | 33.9 MB | 70f33685f3b7 |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 82a86129150c |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-4000/expert_pools.pt | Other | 45.0 MB | 92df4b97a9cb |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | 3bce6fb9623b |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-4000/gating_network.pt | Other | 33.9 MB | 72db9c5c003b |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 9793afb9d64c |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-500/expert_pools.pt | Other | 45.0 MB | 739bc7f5d4b6 |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | 3bce6fb9623b |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-500/gating_network.pt | Other | 33.9 MB | 045e6332b6ab |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/checkpoint-500/scheduler.pt | Other | 1.7 KB | d2c4f1faa352 |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/final_model/expert_pools.pt | Other | 45.0 MB | f827fae07a98 |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/final_model/gated_lora_config.pt | Other | 1.8 KB | 3bce6fb9623b |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/final_model/gating_network.pt | Other | 33.9 MB | 3997b4704c34 |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/final_model/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/visualizations/exp4_gated_loadbalancing_seed2_entropy_per_layer.png | Other | 42.9 KB | bc28b9745a88 |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/visualizations/exp4_gated_loadbalancing_seed2_layer_expert_heatmap.png | Other | 105.1 KB | e044d4e4e80d |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/visualizations/exp4_gated_loadbalancing_seed2_task_expert_usage.png | Other | 43.8 KB | 679a1b24ad37 |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/visualizations/exp4_gated_loadbalancing_seed2_token_routing_1.png | Other | 58.6 KB | dbe34af30cbc |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/visualizations/exp4_gated_loadbalancing_seed2_token_routing_2.png | Other | 58.9 KB | e7f9622c589e |
| legacy/gemma2/exp4_gated_loadbalancing_seed2/visualizations/exp4_gated_loadbalancing_seed2_token_routing_3.png | Other | 59.0 KB | 68ed0dfa26ab |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/best_model/expert_pools.pt | Other | 45.0 MB | 7b85b8011561 |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/best_model/gated_lora_config.pt | Other | 1.8 KB | 3bce6fb9623b |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/best_model/gating_network.pt | Other | 33.9 MB | 4509e031775e |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/best_model/scheduler.pt | Other | 1.7 KB | 3e43ae9e84c6 |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-1000/expert_pools.pt | Other | 45.0 MB | 48cc0bfe3d35 |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | 3bce6fb9623b |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-1000/gating_network.pt | Other | 33.9 MB | ba516dce2012 |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 75d0483a00c8 |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-1500/expert_pools.pt | Other | 45.0 MB | d92d78956699 |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | 3bce6fb9623b |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-1500/gating_network.pt | Other | 33.9 MB | 3c787ad7616a |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-1500/scheduler.pt | Other | 1.7 KB | a930f4a734fe |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-2000/expert_pools.pt | Other | 45.0 MB | fc8282dc6154 |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | 3bce6fb9623b |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-2000/gating_network.pt | Other | 33.9 MB | 975e02ed0af4 |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-2000/scheduler.pt | Other | 1.7 KB | b5ded2205a43 |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-2500/expert_pools.pt | Other | 45.0 MB | 3936a26359c6 |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | 3bce6fb9623b |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-2500/gating_network.pt | Other | 33.9 MB | a035b1a2815b |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 8edb16e6cc0f |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-3000/expert_pools.pt | Other | 45.0 MB | 4596434ca35b |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | 3bce6fb9623b |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-3000/gating_network.pt | Other | 33.9 MB | ed86982e1e97 |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 438e7c9aba3b |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-3500/expert_pools.pt | Other | 45.0 MB | 5c34b06dc653 |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | 3bce6fb9623b |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-3500/gating_network.pt | Other | 33.9 MB | 81463f3efebc |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 82a86129150c |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-4000/expert_pools.pt | Other | 45.0 MB | db61604fd0bb |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | 3bce6fb9623b |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-4000/gating_network.pt | Other | 33.9 MB | 7927bdf165ca |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 9793afb9d64c |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-500/expert_pools.pt | Other | 45.0 MB | f294dd02c381 |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | 3bce6fb9623b |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-500/gating_network.pt | Other | 33.9 MB | b289ba958a26 |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/checkpoint-500/scheduler.pt | Other | 1.7 KB | d2c4f1faa352 |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/final_model/expert_pools.pt | Other | 45.0 MB | 67ccfc518396 |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/final_model/gated_lora_config.pt | Other | 1.8 KB | 3bce6fb9623b |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/final_model/gating_network.pt | Other | 33.9 MB | ebab5e4cbe86 |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/final_model/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/visualizations/exp4_gated_loadbalancing_seed3_entropy_per_layer.png | Other | 43.6 KB | 511727595fe4 |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/visualizations/exp4_gated_loadbalancing_seed3_layer_expert_heatmap.png | Other | 106.8 KB | 15057eb9b500 |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/visualizations/exp4_gated_loadbalancing_seed3_task_expert_usage.png | Other | 44.2 KB | 4c9581e94b3d |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/visualizations/exp4_gated_loadbalancing_seed3_token_routing_1.png | Other | 51.1 KB | 81450be474d9 |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/visualizations/exp4_gated_loadbalancing_seed3_token_routing_2.png | Other | 51.4 KB | 9300be337e41 |
| legacy/gemma2/exp4_gated_loadbalancing_seed3/visualizations/exp4_gated_loadbalancing_seed3_token_routing_3.png | Other | 51.4 KB | 4854d11e4c32 |
| legacy/gemma2/exp5_gated_topk_seed1/best_model/expert_pools.pt | Other | 45.0 MB | 7c85c84fdd6f |
| legacy/gemma2/exp5_gated_topk_seed1/best_model/gated_lora_config.pt | Other | 1.8 KB | 4bc4c620f6ff |
| legacy/gemma2/exp5_gated_topk_seed1/best_model/gating_network.pt | Other | 33.9 MB | 4f87ef160234 |
| legacy/gemma2/exp5_gated_topk_seed1/best_model/scheduler.pt | Other | 1.7 KB | 039753c3afc8 |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-1000/expert_pools.pt | Other | 45.0 MB | 386a0ccc188c |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | 4bc4c620f6ff |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-1000/gating_network.pt | Other | 33.9 MB | aa5987cf19fc |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 75d0483a00c8 |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-1500/expert_pools.pt | Other | 45.0 MB | e2066eb70457 |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | 4bc4c620f6ff |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-1500/gating_network.pt | Other | 33.9 MB | f61733a77cd7 |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-1500/scheduler.pt | Other | 1.7 KB | a930f4a734fe |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-2000/expert_pools.pt | Other | 45.0 MB | ede1597e2bc0 |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | 4bc4c620f6ff |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-2000/gating_network.pt | Other | 33.9 MB | 5438146c1fcf |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-2000/scheduler.pt | Other | 1.7 KB | b5ded2205a43 |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-2500/expert_pools.pt | Other | 45.0 MB | ef7b9be5dd0d |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | 4bc4c620f6ff |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-2500/gating_network.pt | Other | 33.9 MB | c86a95aa7098 |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 8edb16e6cc0f |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-3000/expert_pools.pt | Other | 45.0 MB | bb5ade24a3d7 |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | 4bc4c620f6ff |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-3000/gating_network.pt | Other | 33.9 MB | 046e194cd93b |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 438e7c9aba3b |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-3500/expert_pools.pt | Other | 45.0 MB | 73e42f401840 |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | 4bc4c620f6ff |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-3500/gating_network.pt | Other | 33.9 MB | 7ae937cb412a |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 82a86129150c |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-4000/expert_pools.pt | Other | 45.0 MB | 0bde44ea3000 |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | 4bc4c620f6ff |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-4000/gating_network.pt | Other | 33.9 MB | c5e5687ed61a |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 9793afb9d64c |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-500/expert_pools.pt | Other | 45.0 MB | 03ba99c2518c |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | 4bc4c620f6ff |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-500/gating_network.pt | Other | 33.9 MB | 9a26dd7ffcf3 |
| legacy/gemma2/exp5_gated_topk_seed1/checkpoint-500/scheduler.pt | Other | 1.7 KB | d2c4f1faa352 |
| legacy/gemma2/exp5_gated_topk_seed1/final_model/expert_pools.pt | Other | 45.0 MB | fd3f9cb897cb |
| legacy/gemma2/exp5_gated_topk_seed1/final_model/gated_lora_config.pt | Other | 1.8 KB | 4bc4c620f6ff |
| legacy/gemma2/exp5_gated_topk_seed1/final_model/gating_network.pt | Other | 33.9 MB | e857c81b00b8 |
| legacy/gemma2/exp5_gated_topk_seed1/final_model/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/gemma2/exp5_gated_topk_seed1/visualizations/exp5_gated_topk_seed1_entropy_per_layer.png | Other | 41.4 KB | 76623680322d |
| legacy/gemma2/exp5_gated_topk_seed1/visualizations/exp5_gated_topk_seed1_layer_expert_heatmap.png | Other | 103.2 KB | 2156ef48fdb1 |
| legacy/gemma2/exp5_gated_topk_seed1/visualizations/exp5_gated_topk_seed1_task_expert_usage.png | Other | 41.8 KB | 391152225a39 |
| legacy/gemma2/exp5_gated_topk_seed1/visualizations/exp5_gated_topk_seed1_token_routing_1.png | Other | 45.0 KB | a745057720fa |
| legacy/gemma2/exp5_gated_topk_seed1/visualizations/exp5_gated_topk_seed1_token_routing_2.png | Other | 45.3 KB | ca9b11b1f204 |
| legacy/gemma2/exp5_gated_topk_seed1/visualizations/exp5_gated_topk_seed1_token_routing_3.png | Other | 45.4 KB | 9ef74ca04862 |
| legacy/gemma2/exp5_gated_topk_seed2/best_model/expert_pools.pt | Other | 45.0 MB | a7caae72cf23 |
| legacy/gemma2/exp5_gated_topk_seed2/best_model/gated_lora_config.pt | Other | 1.8 KB | 4bc4c620f6ff |
| legacy/gemma2/exp5_gated_topk_seed2/best_model/gating_network.pt | Other | 33.9 MB | a9a0f5416a8b |
| legacy/gemma2/exp5_gated_topk_seed2/best_model/scheduler.pt | Other | 1.7 KB | d2c4f1faa352 |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-1000/expert_pools.pt | Other | 45.0 MB | 2952bf81a42c |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | 4bc4c620f6ff |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-1000/gating_network.pt | Other | 33.9 MB | 1fabb030697b |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 75d0483a00c8 |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-1500/expert_pools.pt | Other | 45.0 MB | 2b6e05bf5678 |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | 4bc4c620f6ff |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-1500/gating_network.pt | Other | 33.9 MB | 5e4d1a24af47 |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-1500/scheduler.pt | Other | 1.7 KB | a930f4a734fe |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-2000/expert_pools.pt | Other | 45.0 MB | 6049b6e3634d |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | 4bc4c620f6ff |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-2000/gating_network.pt | Other | 33.9 MB | e20dc0b874c3 |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-2000/scheduler.pt | Other | 1.7 KB | b5ded2205a43 |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-2500/expert_pools.pt | Other | 45.0 MB | 5ec07c49afd9 |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | 4bc4c620f6ff |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-2500/gating_network.pt | Other | 33.9 MB | 8fd92fe98617 |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 8edb16e6cc0f |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-3000/expert_pools.pt | Other | 45.0 MB | 3509fb06e0ea |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | 4bc4c620f6ff |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-3000/gating_network.pt | Other | 33.9 MB | 00d10ee41890 |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 438e7c9aba3b |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-3500/expert_pools.pt | Other | 45.0 MB | 5f3f44303c01 |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | 4bc4c620f6ff |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-3500/gating_network.pt | Other | 33.9 MB | 1cd6b898a7b5 |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 82a86129150c |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-4000/expert_pools.pt | Other | 45.0 MB | 085a47887d4f |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | 4bc4c620f6ff |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-4000/gating_network.pt | Other | 33.9 MB | 6aa5e22d580f |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 9793afb9d64c |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-500/expert_pools.pt | Other | 45.0 MB | a7caae72cf23 |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | 4bc4c620f6ff |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-500/gating_network.pt | Other | 33.9 MB | a9a0f5416a8b |
| legacy/gemma2/exp5_gated_topk_seed2/checkpoint-500/scheduler.pt | Other | 1.7 KB | d2c4f1faa352 |
| legacy/gemma2/exp5_gated_topk_seed2/final_model/expert_pools.pt | Other | 45.0 MB | 623461cc8853 |
| legacy/gemma2/exp5_gated_topk_seed2/final_model/gated_lora_config.pt | Other | 1.8 KB | 4bc4c620f6ff |
| legacy/gemma2/exp5_gated_topk_seed2/final_model/gating_network.pt | Other | 33.9 MB | 80f6e4c1665e |
| legacy/gemma2/exp5_gated_topk_seed2/final_model/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/gemma2/exp5_gated_topk_seed2/visualizations/exp5_gated_topk_seed2_entropy_per_layer.png | Other | 42.0 KB | c7ead4486bf3 |
| legacy/gemma2/exp5_gated_topk_seed2/visualizations/exp5_gated_topk_seed2_layer_expert_heatmap.png | Other | 104.2 KB | 1b44f7b656db |
| legacy/gemma2/exp5_gated_topk_seed2/visualizations/exp5_gated_topk_seed2_task_expert_usage.png | Other | 42.9 KB | 90f57ade1ad0 |
| legacy/gemma2/exp5_gated_topk_seed2/visualizations/exp5_gated_topk_seed2_token_routing_1.png | Other | 45.4 KB | b1af681290b4 |
| legacy/gemma2/exp5_gated_topk_seed2/visualizations/exp5_gated_topk_seed2_token_routing_2.png | Other | 45.6 KB | b16c208e8c4b |
| legacy/gemma2/exp5_gated_topk_seed2/visualizations/exp5_gated_topk_seed2_token_routing_3.png | Other | 45.7 KB | 2531a1487a92 |
| legacy/gemma2/exp5_gated_topk_seed3/best_model/expert_pools.pt | Other | 45.0 MB | c20bab8a2467 |
| legacy/gemma2/exp5_gated_topk_seed3/best_model/gated_lora_config.pt | Other | 1.8 KB | 4bc4c620f6ff |
| legacy/gemma2/exp5_gated_topk_seed3/best_model/gating_network.pt | Other | 33.9 MB | 623e2317ea56 |
| legacy/gemma2/exp5_gated_topk_seed3/best_model/scheduler.pt | Other | 1.7 KB | 3e43ae9e84c6 |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-1000/expert_pools.pt | Other | 45.0 MB | 0598537bee59 |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | 4bc4c620f6ff |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-1000/gating_network.pt | Other | 33.9 MB | 92b50abd9c57 |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 75d0483a00c8 |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-1500/expert_pools.pt | Other | 45.0 MB | f888397073dd |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | 4bc4c620f6ff |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-1500/gating_network.pt | Other | 33.9 MB | 83f9275412c8 |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-1500/scheduler.pt | Other | 1.7 KB | a930f4a734fe |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-2000/expert_pools.pt | Other | 45.0 MB | 815a2e3f73d2 |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | 4bc4c620f6ff |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-2000/gating_network.pt | Other | 33.9 MB | 25d15f2477aa |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-2000/scheduler.pt | Other | 1.7 KB | b5ded2205a43 |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-2500/expert_pools.pt | Other | 45.0 MB | 84db21393d8b |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | 4bc4c620f6ff |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-2500/gating_network.pt | Other | 33.9 MB | f278da88746c |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 8edb16e6cc0f |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-3000/expert_pools.pt | Other | 45.0 MB | 13386431ccfa |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | 4bc4c620f6ff |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-3000/gating_network.pt | Other | 33.9 MB | 8fa3299c7426 |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 438e7c9aba3b |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-3500/expert_pools.pt | Other | 45.0 MB | 01f5fed3020c |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | 4bc4c620f6ff |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-3500/gating_network.pt | Other | 33.9 MB | a0834c04aa9c |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 82a86129150c |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-4000/expert_pools.pt | Other | 45.0 MB | aa1946366b9b |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | 4bc4c620f6ff |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-4000/gating_network.pt | Other | 33.9 MB | 964608710705 |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 9793afb9d64c |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-500/expert_pools.pt | Other | 45.0 MB | d92affcafc24 |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | 4bc4c620f6ff |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-500/gating_network.pt | Other | 33.9 MB | 281c27cdc073 |
| legacy/gemma2/exp5_gated_topk_seed3/checkpoint-500/scheduler.pt | Other | 1.7 KB | d2c4f1faa352 |
| legacy/gemma2/exp5_gated_topk_seed3/final_model/expert_pools.pt | Other | 45.0 MB | 23144c58a670 |
| legacy/gemma2/exp5_gated_topk_seed3/final_model/gated_lora_config.pt | Other | 1.8 KB | 4bc4c620f6ff |
| legacy/gemma2/exp5_gated_topk_seed3/final_model/gating_network.pt | Other | 33.9 MB | 7321c0101492 |
| legacy/gemma2/exp5_gated_topk_seed3/final_model/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/gemma2/exp5_gated_topk_seed3/visualizations/exp5_gated_topk_seed3_entropy_per_layer.png | Other | 42.1 KB | 609d81b36570 |
| legacy/gemma2/exp5_gated_topk_seed3/visualizations/exp5_gated_topk_seed3_layer_expert_heatmap.png | Other | 103.6 KB | 9ee5036cf3f2 |
| legacy/gemma2/exp5_gated_topk_seed3/visualizations/exp5_gated_topk_seed3_task_expert_usage.png | Other | 42.2 KB | 9e5743cb8570 |
| legacy/gemma2/exp5_gated_topk_seed3/visualizations/exp5_gated_topk_seed3_token_routing_1.png | Other | 45.5 KB | 702316e1f5da |
| legacy/gemma2/exp5_gated_topk_seed3/visualizations/exp5_gated_topk_seed3_token_routing_2.png | Other | 45.8 KB | ccd939250deb |
| legacy/gemma2/exp5_gated_topk_seed3/visualizations/exp5_gated_topk_seed3_token_routing_3.png | Other | 45.8 KB | 0319b7a6d296 |
| legacy/llama32/exp4_gated_loadbalancing_seed1/best_model/expert_pools.pt | Other | 64.5 MB | 0d766ecc786b |
| legacy/llama32/exp4_gated_loadbalancing_seed1/best_model/gated_lora_config.pt | Other | 1.8 KB | f8397a61a2d0 |
| legacy/llama32/exp4_gated_loadbalancing_seed1/best_model/gating_network.pt | Other | 49.0 MB | bee37304d29e |
| legacy/llama32/exp4_gated_loadbalancing_seed1/best_model/scheduler.pt | Other | 1.7 KB | 2514a309dd4f |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-1000/expert_pools.pt | Other | 64.5 MB | 80048e08fbbb |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | f8397a61a2d0 |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-1000/gating_network.pt | Other | 49.0 MB | 0b8f779093a4 |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 75d0483a00c8 |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-1500/expert_pools.pt | Other | 64.5 MB | f471f93c00bd |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | f8397a61a2d0 |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-1500/gating_network.pt | Other | 49.0 MB | 8d725830632f |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-1500/scheduler.pt | Other | 1.7 KB | a930f4a734fe |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-2000/expert_pools.pt | Other | 64.5 MB | 683e92cbb2e3 |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | f8397a61a2d0 |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-2000/gating_network.pt | Other | 49.0 MB | e9cbee6998a6 |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-2000/scheduler.pt | Other | 1.7 KB | b5ded2205a43 |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-2500/expert_pools.pt | Other | 64.5 MB | 5833badf4fe9 |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | f8397a61a2d0 |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-2500/gating_network.pt | Other | 49.0 MB | a13f2612bbbf |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 8edb16e6cc0f |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-3000/expert_pools.pt | Other | 64.5 MB | db3783a9e036 |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | f8397a61a2d0 |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-3000/gating_network.pt | Other | 49.0 MB | b157b243716c |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 438e7c9aba3b |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-3500/expert_pools.pt | Other | 64.5 MB | fa97f5da8886 |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | f8397a61a2d0 |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-3500/gating_network.pt | Other | 49.0 MB | 65493d57c4b5 |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 82a86129150c |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-4000/expert_pools.pt | Other | 64.5 MB | e4176f88a032 |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | f8397a61a2d0 |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-4000/gating_network.pt | Other | 49.0 MB | 62fefee373d2 |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 9793afb9d64c |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-500/expert_pools.pt | Other | 64.5 MB | 0f31ec4a8f0c |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | f8397a61a2d0 |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-500/gating_network.pt | Other | 49.0 MB | e2ec05062e95 |
| legacy/llama32/exp4_gated_loadbalancing_seed1/checkpoint-500/scheduler.pt | Other | 1.7 KB | d2c4f1faa352 |
| legacy/llama32/exp4_gated_loadbalancing_seed1/final_model/expert_pools.pt | Other | 64.5 MB | 7275ea7d0e50 |
| legacy/llama32/exp4_gated_loadbalancing_seed1/final_model/gated_lora_config.pt | Other | 1.8 KB | f8397a61a2d0 |
| legacy/llama32/exp4_gated_loadbalancing_seed1/final_model/gating_network.pt | Other | 49.0 MB | ef96434547a2 |
| legacy/llama32/exp4_gated_loadbalancing_seed1/final_model/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/llama32/exp4_gated_loadbalancing_seed1/visualizations/exp4_gated_loadbalancing_seed1_entropy_per_layer.png | Other | 43.1 KB | c5d766ce69a6 |
| legacy/llama32/exp4_gated_loadbalancing_seed1/visualizations/exp4_gated_loadbalancing_seed1_layer_expert_heatmap.png | Other | 110.5 KB | a994399d62d0 |
| legacy/llama32/exp4_gated_loadbalancing_seed1/visualizations/exp4_gated_loadbalancing_seed1_task_expert_usage.png | Other | 38.0 KB | 683cb1ff1305 |
| legacy/llama32/exp4_gated_loadbalancing_seed1/visualizations/exp4_gated_loadbalancing_seed1_token_routing_1.png | Other | 94.3 KB | 5b02ea02521b |
| legacy/llama32/exp4_gated_loadbalancing_seed1/visualizations/exp4_gated_loadbalancing_seed1_token_routing_2.png | Other | 94.6 KB | bfef7d86184c |
| legacy/llama32/exp4_gated_loadbalancing_seed1/visualizations/exp4_gated_loadbalancing_seed1_token_routing_3.png | Other | 94.7 KB | 70cf6b16c476 |
| legacy/llama32/exp4_gated_loadbalancing_seed2/best_model/expert_pools.pt | Other | 64.5 MB | d242c8caae8a |
| legacy/llama32/exp4_gated_loadbalancing_seed2/best_model/gated_lora_config.pt | Other | 1.8 KB | f8397a61a2d0 |
| legacy/llama32/exp4_gated_loadbalancing_seed2/best_model/gating_network.pt | Other | 49.0 MB | 1c7eac4e848f |
| legacy/llama32/exp4_gated_loadbalancing_seed2/best_model/scheduler.pt | Other | 1.7 KB | 2514a309dd4f |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-1000/expert_pools.pt | Other | 64.5 MB | aa835552d007 |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | f8397a61a2d0 |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-1000/gating_network.pt | Other | 49.0 MB | f692ae3772cc |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 75d0483a00c8 |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-1500/expert_pools.pt | Other | 64.5 MB | b2117952990e |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | f8397a61a2d0 |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-1500/gating_network.pt | Other | 49.0 MB | cb9f82ed5055 |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-1500/scheduler.pt | Other | 1.7 KB | a930f4a734fe |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-2000/expert_pools.pt | Other | 64.5 MB | 8c60c8218af7 |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | f8397a61a2d0 |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-2000/gating_network.pt | Other | 49.0 MB | 6d2ac31800bb |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-2000/scheduler.pt | Other | 1.7 KB | b5ded2205a43 |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-2500/expert_pools.pt | Other | 64.5 MB | c6b1051873b7 |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | f8397a61a2d0 |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-2500/gating_network.pt | Other | 49.0 MB | 7f813adfd0ec |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 8edb16e6cc0f |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-3000/expert_pools.pt | Other | 64.5 MB | 45959678a1d2 |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | f8397a61a2d0 |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-3000/gating_network.pt | Other | 49.0 MB | b564cd4c8f6f |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 438e7c9aba3b |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-3500/expert_pools.pt | Other | 64.5 MB | c281235d0737 |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | f8397a61a2d0 |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-3500/gating_network.pt | Other | 49.0 MB | c50919174b21 |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 82a86129150c |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-4000/expert_pools.pt | Other | 64.5 MB | 84516926c987 |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | f8397a61a2d0 |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-4000/gating_network.pt | Other | 49.0 MB | 67e6ce35932e |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 9793afb9d64c |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-500/expert_pools.pt | Other | 64.5 MB | abd71f46e55f |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | f8397a61a2d0 |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-500/gating_network.pt | Other | 49.0 MB | 13cfcab995df |
| legacy/llama32/exp4_gated_loadbalancing_seed2/checkpoint-500/scheduler.pt | Other | 1.7 KB | d2c4f1faa352 |
| legacy/llama32/exp4_gated_loadbalancing_seed2/final_model/expert_pools.pt | Other | 64.5 MB | de0a8ff5d9b5 |
| legacy/llama32/exp4_gated_loadbalancing_seed2/final_model/gated_lora_config.pt | Other | 1.8 KB | f8397a61a2d0 |
| legacy/llama32/exp4_gated_loadbalancing_seed2/final_model/gating_network.pt | Other | 49.0 MB | b598e4266cd3 |
| legacy/llama32/exp4_gated_loadbalancing_seed2/final_model/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/llama32/exp4_gated_loadbalancing_seed2/visualizations/exp4_gated_loadbalancing_seed2_entropy_per_layer.png | Other | 43.1 KB | c324664d4057 |
| legacy/llama32/exp4_gated_loadbalancing_seed2/visualizations/exp4_gated_loadbalancing_seed2_layer_expert_heatmap.png | Other | 109.0 KB | 755b7d719e55 |
| legacy/llama32/exp4_gated_loadbalancing_seed2/visualizations/exp4_gated_loadbalancing_seed2_task_expert_usage.png | Other | 37.8 KB | 2573d6493b29 |
| legacy/llama32/exp4_gated_loadbalancing_seed2/visualizations/exp4_gated_loadbalancing_seed2_token_routing_1.png | Other | 94.8 KB | 8529a6acedb6 |
| legacy/llama32/exp4_gated_loadbalancing_seed2/visualizations/exp4_gated_loadbalancing_seed2_token_routing_2.png | Other | 95.1 KB | 33d555706b3f |
| legacy/llama32/exp4_gated_loadbalancing_seed2/visualizations/exp4_gated_loadbalancing_seed2_token_routing_3.png | Other | 95.1 KB | d36211d4f1b6 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/best_model/expert_pools.pt | Other | 64.5 MB | e4f79f8640b6 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/best_model/gated_lora_config.pt | Other | 1.8 KB | f8397a61a2d0 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/best_model/gating_network.pt | Other | 49.0 MB | 905552fd0020 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/best_model/scheduler.pt | Other | 1.7 KB | 2514a309dd4f |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-1000/expert_pools.pt | Other | 64.5 MB | 0b7441f33f57 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | f8397a61a2d0 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-1000/gating_network.pt | Other | 49.0 MB | 9a973b354c64 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 75d0483a00c8 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-1500/expert_pools.pt | Other | 64.5 MB | 1a14ad8e4f9a |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | f8397a61a2d0 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-1500/gating_network.pt | Other | 49.0 MB | f4add5695415 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-1500/scheduler.pt | Other | 1.7 KB | a930f4a734fe |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-2000/expert_pools.pt | Other | 64.5 MB | 40dc65679f60 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | f8397a61a2d0 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-2000/gating_network.pt | Other | 49.0 MB | 4c9c7c9f9153 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-2000/scheduler.pt | Other | 1.7 KB | b5ded2205a43 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-2500/expert_pools.pt | Other | 64.5 MB | c27e0776e3e7 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | f8397a61a2d0 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-2500/gating_network.pt | Other | 49.0 MB | 459828b1dd18 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 8edb16e6cc0f |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-3000/expert_pools.pt | Other | 64.5 MB | 33da80528244 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | f8397a61a2d0 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-3000/gating_network.pt | Other | 49.0 MB | 3cfdc17c9c26 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 438e7c9aba3b |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-3500/expert_pools.pt | Other | 64.5 MB | 7fd37f85a404 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | f8397a61a2d0 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-3500/gating_network.pt | Other | 49.0 MB | 11a62ebaf321 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 82a86129150c |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-4000/expert_pools.pt | Other | 64.5 MB | ede3f047a06d |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | f8397a61a2d0 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-4000/gating_network.pt | Other | 49.0 MB | ba76c5939d85 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 9793afb9d64c |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-500/expert_pools.pt | Other | 64.5 MB | 2833e2129699 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | f8397a61a2d0 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-500/gating_network.pt | Other | 49.0 MB | a5386dd311a1 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/checkpoint-500/scheduler.pt | Other | 1.7 KB | d2c4f1faa352 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/final_model/expert_pools.pt | Other | 64.5 MB | 08114e64921f |
| legacy/llama32/exp4_gated_loadbalancing_seed3/final_model/gated_lora_config.pt | Other | 1.8 KB | f8397a61a2d0 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/final_model/gating_network.pt | Other | 49.0 MB | 35f2d0ad7725 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/final_model/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/visualizations/exp4_gated_loadbalancing_seed3_entropy_per_layer.png | Other | 43.5 KB | 562ebb26c482 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/visualizations/exp4_gated_loadbalancing_seed3_layer_expert_heatmap.png | Other | 109.2 KB | b62bf8c8260d |
| legacy/llama32/exp4_gated_loadbalancing_seed3/visualizations/exp4_gated_loadbalancing_seed3_task_expert_usage.png | Other | 38.2 KB | ad9445318577 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/visualizations/exp4_gated_loadbalancing_seed3_token_routing_1.png | Other | 95.3 KB | 088f744a7596 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/visualizations/exp4_gated_loadbalancing_seed3_token_routing_2.png | Other | 95.5 KB | 4191d781afa3 |
| legacy/llama32/exp4_gated_loadbalancing_seed3/visualizations/exp4_gated_loadbalancing_seed3_token_routing_3.png | Other | 95.6 KB | 4bc5cad6fc6c |
| legacy/llama32/exp5_gated_topk_seed1/best_model/expert_pools.pt | Other | 64.5 MB | e31fab0e5df1 |
| legacy/llama32/exp5_gated_topk_seed1/best_model/gated_lora_config.pt | Other | 1.8 KB | 086f8a5d1324 |
| legacy/llama32/exp5_gated_topk_seed1/best_model/gating_network.pt | Other | 49.0 MB | 6d52a123c421 |
| legacy/llama32/exp5_gated_topk_seed1/best_model/scheduler.pt | Other | 1.7 KB | 925b6912f2d8 |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-1000/expert_pools.pt | Other | 64.5 MB | 608f18564bb3 |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | 086f8a5d1324 |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-1000/gating_network.pt | Other | 49.0 MB | d835af6cd4fd |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 75d0483a00c8 |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-1500/expert_pools.pt | Other | 64.5 MB | 313ebe5c4070 |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | 086f8a5d1324 |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-1500/gating_network.pt | Other | 49.0 MB | 59477ce7c4a4 |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-1500/scheduler.pt | Other | 1.7 KB | a930f4a734fe |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-2000/expert_pools.pt | Other | 64.5 MB | b3f2c4a98db0 |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | 086f8a5d1324 |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-2000/gating_network.pt | Other | 49.0 MB | 1eb4bcb7b618 |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-2000/scheduler.pt | Other | 1.7 KB | b5ded2205a43 |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-2500/expert_pools.pt | Other | 64.5 MB | 1b6a82be6c20 |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | 086f8a5d1324 |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-2500/gating_network.pt | Other | 49.0 MB | 2dab187f6a43 |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 8edb16e6cc0f |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-3000/expert_pools.pt | Other | 64.5 MB | c0d3a82c899c |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | 086f8a5d1324 |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-3000/gating_network.pt | Other | 49.0 MB | 8156b771f88e |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 438e7c9aba3b |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-3500/expert_pools.pt | Other | 64.5 MB | e46799baf557 |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | 086f8a5d1324 |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-3500/gating_network.pt | Other | 49.0 MB | 52e62e2f6e1d |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 82a86129150c |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-4000/expert_pools.pt | Other | 64.5 MB | 7a3f0108df65 |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | 086f8a5d1324 |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-4000/gating_network.pt | Other | 49.0 MB | 89a5bb446101 |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 9793afb9d64c |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-500/expert_pools.pt | Other | 64.5 MB | f16aa5354f62 |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | 086f8a5d1324 |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-500/gating_network.pt | Other | 49.0 MB | 871e72024cc6 |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-500/scheduler.pt | Other | 1.7 KB | d2c4f1faa352 |
| legacy/llama32/exp5_gated_topk_seed1/final_model/expert_pools.pt | Other | 64.5 MB | e3cc231c3fb7 |
| legacy/llama32/exp5_gated_topk_seed1/final_model/gated_lora_config.pt | Other | 1.8 KB | 086f8a5d1324 |
| legacy/llama32/exp5_gated_topk_seed1/final_model/gating_network.pt | Other | 49.0 MB | bbec5b3e8072 |
| legacy/llama32/exp5_gated_topk_seed1/final_model/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/llama32/exp5_gated_topk_seed1/visualizations/exp5_gated_topk_seed1_entropy_per_layer.png | Other | 42.2 KB | 146a5b23e03f |
| legacy/llama32/exp5_gated_topk_seed1/visualizations/exp5_gated_topk_seed1_layer_expert_heatmap.png | Other | 107.4 KB | cf98c1d43c44 |
| legacy/llama32/exp5_gated_topk_seed1/visualizations/exp5_gated_topk_seed1_task_expert_usage.png | Other | 43.0 KB | 4d312379d7ee |
| legacy/llama32/exp5_gated_topk_seed1/visualizations/exp5_gated_topk_seed1_token_routing_1.png | Other | 94.0 KB | ecce9f326df8 |
| legacy/llama32/exp5_gated_topk_seed1/visualizations/exp5_gated_topk_seed1_token_routing_2.png | Other | 94.4 KB | 99aad2a75b65 |
| legacy/llama32/exp5_gated_topk_seed1/visualizations/exp5_gated_topk_seed1_token_routing_3.png | Other | 94.4 KB | f293b25fd6b8 |
| legacy/llama32/exp5_gated_topk_seed2/best_model/expert_pools.pt | Other | 64.5 MB | d226d889bce8 |
| legacy/llama32/exp5_gated_topk_seed2/best_model/gated_lora_config.pt | Other | 1.8 KB | 086f8a5d1324 |
| legacy/llama32/exp5_gated_topk_seed2/best_model/gating_network.pt | Other | 49.0 MB | 19bd07246cdc |
| legacy/llama32/exp5_gated_topk_seed2/best_model/scheduler.pt | Other | 1.7 KB | 256b90657b80 |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-1000/expert_pools.pt | Other | 64.5 MB | 2c2c888aa3d7 |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | 086f8a5d1324 |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-1000/gating_network.pt | Other | 49.0 MB | 1d47079f0e31 |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 75d0483a00c8 |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-1500/expert_pools.pt | Other | 64.5 MB | c87c0e0bc2b5 |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | 086f8a5d1324 |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-1500/gating_network.pt | Other | 49.0 MB | e855669114a2 |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-1500/scheduler.pt | Other | 1.7 KB | a930f4a734fe |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-2000/expert_pools.pt | Other | 64.5 MB | 7f281910c740 |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | 086f8a5d1324 |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-2000/gating_network.pt | Other | 49.0 MB | c2462be16e5d |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-2000/scheduler.pt | Other | 1.7 KB | b5ded2205a43 |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-2500/expert_pools.pt | Other | 64.5 MB | 34e5d035effd |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | 086f8a5d1324 |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-2500/gating_network.pt | Other | 49.0 MB | e3595af97402 |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 8edb16e6cc0f |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-3000/expert_pools.pt | Other | 64.5 MB | 44d652772422 |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | 086f8a5d1324 |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-3000/gating_network.pt | Other | 49.0 MB | 62b23e980d18 |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 438e7c9aba3b |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-3500/expert_pools.pt | Other | 64.5 MB | 3a4160bae924 |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | 086f8a5d1324 |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-3500/gating_network.pt | Other | 49.0 MB | 18fb382b152d |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 82a86129150c |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-4000/expert_pools.pt | Other | 64.5 MB | 4a8367459788 |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | 086f8a5d1324 |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-4000/gating_network.pt | Other | 49.0 MB | c40898ec505a |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 9793afb9d64c |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-500/expert_pools.pt | Other | 64.5 MB | 12b93f4e9b89 |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | 086f8a5d1324 |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-500/gating_network.pt | Other | 49.0 MB | fe53905e58b9 |
| legacy/llama32/exp5_gated_topk_seed2/checkpoint-500/scheduler.pt | Other | 1.7 KB | d2c4f1faa352 |
| legacy/llama32/exp5_gated_topk_seed2/final_model/expert_pools.pt | Other | 64.5 MB | 64ff657589df |
| legacy/llama32/exp5_gated_topk_seed2/final_model/gated_lora_config.pt | Other | 1.8 KB | 086f8a5d1324 |
| legacy/llama32/exp5_gated_topk_seed2/final_model/gating_network.pt | Other | 49.0 MB | 98016e967daa |
| legacy/llama32/exp5_gated_topk_seed2/final_model/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/llama32/exp5_gated_topk_seed2/visualizations/exp5_gated_topk_seed2_entropy_per_layer.png | Other | 42.2 KB | 24caaeb2c2a8 |
| legacy/llama32/exp5_gated_topk_seed2/visualizations/exp5_gated_topk_seed2_layer_expert_heatmap.png | Other | 108.1 KB | 3a5b65f0b55e |
| legacy/llama32/exp5_gated_topk_seed2/visualizations/exp5_gated_topk_seed2_task_expert_usage.png | Other | 44.0 KB | d3f62189111b |
| legacy/llama32/exp5_gated_topk_seed2/visualizations/exp5_gated_topk_seed2_token_routing_1.png | Other | 94.5 KB | a686f8e84477 |
| legacy/llama32/exp5_gated_topk_seed2/visualizations/exp5_gated_topk_seed2_token_routing_2.png | Other | 94.8 KB | a5e0afd4cbec |
| legacy/llama32/exp5_gated_topk_seed2/visualizations/exp5_gated_topk_seed2_token_routing_3.png | Other | 94.9 KB | aaa8df72d609 |
| legacy/llama32/exp5_gated_topk_seed3/best_model/expert_pools.pt | Other | 64.5 MB | ead921469abd |
| legacy/llama32/exp5_gated_topk_seed3/best_model/gated_lora_config.pt | Other | 1.8 KB | 086f8a5d1324 |
| legacy/llama32/exp5_gated_topk_seed3/best_model/gating_network.pt | Other | 49.0 MB | 8c5f0e6530a2 |
| legacy/llama32/exp5_gated_topk_seed3/best_model/scheduler.pt | Other | 1.7 KB | 256b90657b80 |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-1000/expert_pools.pt | Other | 64.5 MB | ec6778bcc143 |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | 086f8a5d1324 |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-1000/gating_network.pt | Other | 49.0 MB | 6a155763b163 |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 75d0483a00c8 |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-1500/expert_pools.pt | Other | 64.5 MB | 9a5650a9897b |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | 086f8a5d1324 |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-1500/gating_network.pt | Other | 49.0 MB | 5c82171e2e88 |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-1500/scheduler.pt | Other | 1.7 KB | a930f4a734fe |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-2000/expert_pools.pt | Other | 64.5 MB | 70b0f7706383 |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | 086f8a5d1324 |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-2000/gating_network.pt | Other | 49.0 MB | b077050c42ab |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-2000/scheduler.pt | Other | 1.7 KB | b5ded2205a43 |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-2500/expert_pools.pt | Other | 64.5 MB | 720598de928f |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | 086f8a5d1324 |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-2500/gating_network.pt | Other | 49.0 MB | 696e0e75e364 |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 8edb16e6cc0f |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-3000/expert_pools.pt | Other | 64.5 MB | c0ec9e5e7a2d |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | 086f8a5d1324 |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-3000/gating_network.pt | Other | 49.0 MB | be8cb0509a49 |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 438e7c9aba3b |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-3500/expert_pools.pt | Other | 64.5 MB | 6ddfd304c835 |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | 086f8a5d1324 |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-3500/gating_network.pt | Other | 49.0 MB | d9e348da4c22 |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 82a86129150c |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-4000/expert_pools.pt | Other | 64.5 MB | 53924f09c0b7 |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | 086f8a5d1324 |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-4000/gating_network.pt | Other | 49.0 MB | b8aee9ba2f35 |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 9793afb9d64c |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-500/expert_pools.pt | Other | 64.5 MB | 161157758ec2 |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | 086f8a5d1324 |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-500/gating_network.pt | Other | 49.0 MB | 55069b5071a9 |
| legacy/llama32/exp5_gated_topk_seed3/checkpoint-500/scheduler.pt | Other | 1.7 KB | d2c4f1faa352 |
| legacy/llama32/exp5_gated_topk_seed3/final_model/expert_pools.pt | Other | 64.5 MB | 6ede4455b64c |
| legacy/llama32/exp5_gated_topk_seed3/final_model/gated_lora_config.pt | Other | 1.8 KB | 086f8a5d1324 |
| legacy/llama32/exp5_gated_topk_seed3/final_model/gating_network.pt | Other | 49.0 MB | d32214591c23 |
| legacy/llama32/exp5_gated_topk_seed3/final_model/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/llama32/exp5_gated_topk_seed3/visualizations/exp5_gated_topk_seed3_entropy_per_layer.png | Other | 42.0 KB | 2dc1b37af3ea |
| legacy/llama32/exp5_gated_topk_seed3/visualizations/exp5_gated_topk_seed3_layer_expert_heatmap.png | Other | 107.3 KB | 545c96636c0b |
| legacy/llama32/exp5_gated_topk_seed3/visualizations/exp5_gated_topk_seed3_task_expert_usage.png | Other | 43.3 KB | 554cec393476 |
| legacy/llama32/exp5_gated_topk_seed3/visualizations/exp5_gated_topk_seed3_token_routing_1.png | Other | 94.4 KB | 9aa26977f625 |
| legacy/llama32/exp5_gated_topk_seed3/visualizations/exp5_gated_topk_seed3_token_routing_2.png | Other | 94.7 KB | 30d712015aea |
| legacy/llama32/exp5_gated_topk_seed3/visualizations/exp5_gated_topk_seed3_token_routing_3.png | Other | 94.7 KB | 53d6ac604600 |
| legacy/llama32_modified/ablation_partial_gating_seed1/TRAINING_DONE | Other | 111 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed1/best_model/expert_pools.pt | Other | 64.5 MB | 41ce4e0651cd |
| legacy/llama32_modified/ablation_partial_gating_seed1/best_model/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed1/best_model/gating_network.pt | Other | 49.0 MB | 310c51044020 |
| legacy/llama32_modified/ablation_partial_gating_seed1/best_model/scheduler.pt | Other | 1.7 KB | 9cfe7f6241e3 |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-1000/expert_pools.pt | Other | 64.5 MB | 46a8130b4df6 |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-1000/gating_network.pt | Other | 49.0 MB | 6d31ef8caf32 |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 75d0483a00c8 |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-1500/expert_pools.pt | Other | 64.5 MB | f5c536404445 |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-1500/gating_network.pt | Other | 49.0 MB | a15e7cb4cdcd |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-1500/scheduler.pt | Other | 1.7 KB | a930f4a734fe |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-2000/expert_pools.pt | Other | 64.5 MB | ede1986a0e91 |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-2000/gating_network.pt | Other | 49.0 MB | 86fd6c2b1ea0 |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-2000/scheduler.pt | Other | 1.7 KB | b5ded2205a43 |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-2500/expert_pools.pt | Other | 64.5 MB | 0b4ebd88cf8e |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-2500/gating_network.pt | Other | 49.0 MB | 28c52ae53e09 |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 8edb16e6cc0f |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-3000/expert_pools.pt | Other | 64.5 MB | 3626bd019479 |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-3000/gating_network.pt | Other | 49.0 MB | c37b2017019c |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 438e7c9aba3b |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-3500/expert_pools.pt | Other | 64.5 MB | 50562fde64e9 |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-3500/gating_network.pt | Other | 49.0 MB | 5016ad5273d3 |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 82a86129150c |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-4000/expert_pools.pt | Other | 64.5 MB | 648948198bca |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-4000/gating_network.pt | Other | 49.0 MB | f6dd00b82534 |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 9793afb9d64c |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-500/expert_pools.pt | Other | 64.5 MB | 08db63f685ae |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-500/gating_network.pt | Other | 49.0 MB | 4f9764b6b5a9 |
| legacy/llama32_modified/ablation_partial_gating_seed1/checkpoint-500/scheduler.pt | Other | 1.7 KB | d2c4f1faa352 |
| legacy/llama32_modified/ablation_partial_gating_seed1/epoch-1/expert_pools.pt | Other | 64.5 MB | 44381d9d8d81 |
| legacy/llama32_modified/ablation_partial_gating_seed1/epoch-1/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed1/epoch-1/gating_network.pt | Other | 49.0 MB | 181ac46d9260 |
| legacy/llama32_modified/ablation_partial_gating_seed1/epoch-1/scheduler.pt | Other | 1.7 KB | 86f6731f97de |
| legacy/llama32_modified/ablation_partial_gating_seed1/epoch-2/expert_pools.pt | Other | 64.5 MB | a80732f85112 |
| legacy/llama32_modified/ablation_partial_gating_seed1/epoch-2/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed1/epoch-2/gating_network.pt | Other | 49.0 MB | 8493e97b55c3 |
| legacy/llama32_modified/ablation_partial_gating_seed1/epoch-2/scheduler.pt | Other | 1.7 KB | 61c7ee9cc021 |
| legacy/llama32_modified/ablation_partial_gating_seed1/epoch-3/expert_pools.pt | Other | 64.5 MB | 800f6a32b356 |
| legacy/llama32_modified/ablation_partial_gating_seed1/epoch-3/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed1/epoch-3/gating_network.pt | Other | 49.0 MB | 2844a3730373 |
| legacy/llama32_modified/ablation_partial_gating_seed1/epoch-3/scheduler.pt | Other | 1.7 KB | 3166389b2e94 |
| legacy/llama32_modified/ablation_partial_gating_seed1/epoch-4/expert_pools.pt | Other | 64.5 MB | 34b1f4ac1cc4 |
| legacy/llama32_modified/ablation_partial_gating_seed1/epoch-4/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed1/epoch-4/gating_network.pt | Other | 49.0 MB | ac7b77ae5d78 |
| legacy/llama32_modified/ablation_partial_gating_seed1/epoch-4/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/llama32_modified/ablation_partial_gating_seed1/final_model/expert_pools.pt | Other | 64.5 MB | 34b1f4ac1cc4 |
| legacy/llama32_modified/ablation_partial_gating_seed1/final_model/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed1/final_model/gating_network.pt | Other | 49.0 MB | ac7b77ae5d78 |
| legacy/llama32_modified/ablation_partial_gating_seed1/final_model/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/llama32_modified/ablation_partial_gating_seed1/latest/expert_pools.pt | Other | 64.5 MB | 800f6a32b356 |
| legacy/llama32_modified/ablation_partial_gating_seed1/latest/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed1/latest/gating_network.pt | Other | 49.0 MB | 2844a3730373 |
| legacy/llama32_modified/ablation_partial_gating_seed1/latest/scheduler.pt | Other | 1.7 KB | 3166389b2e94 |
| legacy/llama32_modified/ablation_partial_gating_seed1/visualizations/ablation_partial_gating_seed1_entropy_per_layer.png | Other | 41.2 KB | 270a944d8eb6 |
| legacy/llama32_modified/ablation_partial_gating_seed1/visualizations/ablation_partial_gating_seed1_layer_expert_heatmap.png | Other | 107.9 KB | 6e463c9cb268 |
| legacy/llama32_modified/ablation_partial_gating_seed1/visualizations/ablation_partial_gating_seed1_task_expert_usage.png | Other | 40.8 KB | da0def403a7a |
| legacy/llama32_modified/ablation_partial_gating_seed1/visualizations/ablation_partial_gating_seed1_token_routing_1.png | Other | 96.1 KB | 7d88e879eb78 |
| legacy/llama32_modified/ablation_partial_gating_seed1/visualizations/ablation_partial_gating_seed1_token_routing_2.png | Other | 96.4 KB | 0062bcd2298d |
| legacy/llama32_modified/ablation_partial_gating_seed1/visualizations/ablation_partial_gating_seed1_token_routing_3.png | Other | 96.4 KB | f85aa88117dd |
| legacy/llama32_modified/ablation_partial_gating_seed2/TRAINING_DONE | Other | 111 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed2/best_model/expert_pools.pt | Other | 64.5 MB | ac4954e23fab |
| legacy/llama32_modified/ablation_partial_gating_seed2/best_model/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed2/best_model/gating_network.pt | Other | 49.0 MB | 87458d54a175 |
| legacy/llama32_modified/ablation_partial_gating_seed2/best_model/scheduler.pt | Other | 1.7 KB | 18e42a717ff0 |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-1000/expert_pools.pt | Other | 64.5 MB | 24840b7baa7c |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-1000/gating_network.pt | Other | 49.0 MB | 681ae53c23e6 |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 75d0483a00c8 |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-1500/expert_pools.pt | Other | 64.5 MB | 6056181f0d44 |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-1500/gating_network.pt | Other | 49.0 MB | 6d214ad18220 |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-1500/scheduler.pt | Other | 1.7 KB | a930f4a734fe |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-2000/expert_pools.pt | Other | 64.5 MB | d4a34c76d227 |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-2000/gating_network.pt | Other | 49.0 MB | 11877204e4cd |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-2000/scheduler.pt | Other | 1.7 KB | b5ded2205a43 |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-2500/expert_pools.pt | Other | 64.5 MB | bfe1e66e237d |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-2500/gating_network.pt | Other | 49.0 MB | 099ead682314 |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 8edb16e6cc0f |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-3000/expert_pools.pt | Other | 64.5 MB | 36235ab2d47c |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-3000/gating_network.pt | Other | 49.0 MB | 98f158815d06 |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 438e7c9aba3b |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-3500/expert_pools.pt | Other | 64.5 MB | a1177b67914c |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-3500/gating_network.pt | Other | 49.0 MB | 37d3bae2ab93 |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 82a86129150c |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-4000/expert_pools.pt | Other | 64.5 MB | 93a4cd64bd57 |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-4000/gating_network.pt | Other | 49.0 MB | d4969ba6abfe |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 9793afb9d64c |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-500/expert_pools.pt | Other | 64.5 MB | 6b6d3fada213 |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-500/gating_network.pt | Other | 49.0 MB | ac4e3852aaa0 |
| legacy/llama32_modified/ablation_partial_gating_seed2/checkpoint-500/scheduler.pt | Other | 1.7 KB | d2c4f1faa352 |
| legacy/llama32_modified/ablation_partial_gating_seed2/epoch-1/expert_pools.pt | Other | 64.5 MB | 7d20f6399afd |
| legacy/llama32_modified/ablation_partial_gating_seed2/epoch-1/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed2/epoch-1/gating_network.pt | Other | 49.0 MB | b35daaeedcd0 |
| legacy/llama32_modified/ablation_partial_gating_seed2/epoch-1/scheduler.pt | Other | 1.7 KB | 86f6731f97de |
| legacy/llama32_modified/ablation_partial_gating_seed2/epoch-2/expert_pools.pt | Other | 64.5 MB | e2309d70ba1f |
| legacy/llama32_modified/ablation_partial_gating_seed2/epoch-2/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed2/epoch-2/gating_network.pt | Other | 49.0 MB | 357be4fb5661 |
| legacy/llama32_modified/ablation_partial_gating_seed2/epoch-2/scheduler.pt | Other | 1.7 KB | 61c7ee9cc021 |
| legacy/llama32_modified/ablation_partial_gating_seed2/epoch-3/expert_pools.pt | Other | 64.5 MB | 7b1aaed8104c |
| legacy/llama32_modified/ablation_partial_gating_seed2/epoch-3/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed2/epoch-3/gating_network.pt | Other | 49.0 MB | 6cde71d94712 |
| legacy/llama32_modified/ablation_partial_gating_seed2/epoch-3/scheduler.pt | Other | 1.7 KB | 3166389b2e94 |
| legacy/llama32_modified/ablation_partial_gating_seed2/epoch-4/expert_pools.pt | Other | 64.5 MB | dcd13e66130c |
| legacy/llama32_modified/ablation_partial_gating_seed2/epoch-4/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed2/epoch-4/gating_network.pt | Other | 49.0 MB | f0ba860705f7 |
| legacy/llama32_modified/ablation_partial_gating_seed2/epoch-4/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/llama32_modified/ablation_partial_gating_seed2/final_model/expert_pools.pt | Other | 64.5 MB | dcd13e66130c |
| legacy/llama32_modified/ablation_partial_gating_seed2/final_model/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed2/final_model/gating_network.pt | Other | 49.0 MB | f0ba860705f7 |
| legacy/llama32_modified/ablation_partial_gating_seed2/final_model/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/llama32_modified/ablation_partial_gating_seed2/latest/expert_pools.pt | Other | 64.5 MB | 7b1aaed8104c |
| legacy/llama32_modified/ablation_partial_gating_seed2/latest/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed2/latest/gating_network.pt | Other | 49.0 MB | 6cde71d94712 |
| legacy/llama32_modified/ablation_partial_gating_seed2/latest/scheduler.pt | Other | 1.7 KB | 3166389b2e94 |
| legacy/llama32_modified/ablation_partial_gating_seed2/visualizations/ablation_partial_gating_seed2_entropy_per_layer.png | Other | 42.3 KB | 9c4dbd374a43 |
| legacy/llama32_modified/ablation_partial_gating_seed2/visualizations/ablation_partial_gating_seed2_layer_expert_heatmap.png | Other | 110.5 KB | 99db23c6696b |
| legacy/llama32_modified/ablation_partial_gating_seed2/visualizations/ablation_partial_gating_seed2_task_expert_usage.png | Other | 42.7 KB | af8f918156cb |
| legacy/llama32_modified/ablation_partial_gating_seed2/visualizations/ablation_partial_gating_seed2_token_routing_1.png | Other | 95.7 KB | 02df57b8ddd1 |
| legacy/llama32_modified/ablation_partial_gating_seed2/visualizations/ablation_partial_gating_seed2_token_routing_2.png | Other | 96.0 KB | d0ecfadaf50b |
| legacy/llama32_modified/ablation_partial_gating_seed2/visualizations/ablation_partial_gating_seed2_token_routing_3.png | Other | 96.1 KB | b50af141beca |
| legacy/llama32_modified/ablation_partial_gating_seed3/TRAINING_DONE | Other | 111 B | — |
| legacy/llama32_modified/ablation_partial_gating_seed3/best_model/expert_pools.pt | Other | 64.5 MB | d3e9f6e6d9f2 |
| legacy/llama32_modified/ablation_partial_gating_seed3/best_model/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed3/best_model/gating_network.pt | Other | 49.0 MB | ebe961971846 |
| legacy/llama32_modified/ablation_partial_gating_seed3/best_model/scheduler.pt | Other | 1.7 KB | 482234865e56 |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-1000/expert_pools.pt | Other | 64.5 MB | 384f9d0ec787 |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-1000/gating_network.pt | Other | 49.0 MB | 3936ce9cbdab |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 75d0483a00c8 |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-1500/expert_pools.pt | Other | 64.5 MB | f10bea1e6148 |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-1500/gating_network.pt | Other | 49.0 MB | eabe91614e0d |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-1500/scheduler.pt | Other | 1.7 KB | a930f4a734fe |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-2000/expert_pools.pt | Other | 64.5 MB | e0346f0ae7c0 |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-2000/gating_network.pt | Other | 49.0 MB | 51ba8f3510b3 |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-2000/scheduler.pt | Other | 1.7 KB | b5ded2205a43 |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-2500/expert_pools.pt | Other | 64.5 MB | f1810be7a960 |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-2500/gating_network.pt | Other | 49.0 MB | cf2953d85485 |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 8edb16e6cc0f |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-3000/expert_pools.pt | Other | 64.5 MB | f46951f6b8e3 |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-3000/gating_network.pt | Other | 49.0 MB | e6b80d8c1e9e |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 438e7c9aba3b |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-3500/expert_pools.pt | Other | 64.5 MB | 7c81ea6a1174 |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-3500/gating_network.pt | Other | 49.0 MB | 41f67e8369a6 |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 82a86129150c |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-4000/expert_pools.pt | Other | 64.5 MB | ad3c876e6271 |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-4000/gating_network.pt | Other | 49.0 MB | abd0045f8cba |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 9793afb9d64c |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-500/expert_pools.pt | Other | 64.5 MB | a4fba24d614f |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-500/gating_network.pt | Other | 49.0 MB | 90088b3c51c7 |
| legacy/llama32_modified/ablation_partial_gating_seed3/checkpoint-500/scheduler.pt | Other | 1.7 KB | d2c4f1faa352 |
| legacy/llama32_modified/ablation_partial_gating_seed3/epoch-1/expert_pools.pt | Other | 64.5 MB | bcfd27a6c015 |
| legacy/llama32_modified/ablation_partial_gating_seed3/epoch-1/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed3/epoch-1/gating_network.pt | Other | 49.0 MB | d324555e6e98 |
| legacy/llama32_modified/ablation_partial_gating_seed3/epoch-1/scheduler.pt | Other | 1.7 KB | 86f6731f97de |
| legacy/llama32_modified/ablation_partial_gating_seed3/epoch-2/expert_pools.pt | Other | 64.5 MB | bf24112318e4 |
| legacy/llama32_modified/ablation_partial_gating_seed3/epoch-2/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed3/epoch-2/gating_network.pt | Other | 49.0 MB | d21c0e411ad1 |
| legacy/llama32_modified/ablation_partial_gating_seed3/epoch-2/scheduler.pt | Other | 1.7 KB | 61c7ee9cc021 |
| legacy/llama32_modified/ablation_partial_gating_seed3/epoch-3/expert_pools.pt | Other | 64.5 MB | 75cc0ceda86c |
| legacy/llama32_modified/ablation_partial_gating_seed3/epoch-3/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed3/epoch-3/gating_network.pt | Other | 49.0 MB | ad33cf380355 |
| legacy/llama32_modified/ablation_partial_gating_seed3/epoch-3/scheduler.pt | Other | 1.7 KB | 3166389b2e94 |
| legacy/llama32_modified/ablation_partial_gating_seed3/epoch-4/expert_pools.pt | Other | 64.5 MB | 8110ebf7de32 |
| legacy/llama32_modified/ablation_partial_gating_seed3/epoch-4/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed3/epoch-4/gating_network.pt | Other | 49.0 MB | 36faea8202d1 |
| legacy/llama32_modified/ablation_partial_gating_seed3/epoch-4/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/llama32_modified/ablation_partial_gating_seed3/final_model/expert_pools.pt | Other | 64.5 MB | 8110ebf7de32 |
| legacy/llama32_modified/ablation_partial_gating_seed3/final_model/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed3/final_model/gating_network.pt | Other | 49.0 MB | 36faea8202d1 |
| legacy/llama32_modified/ablation_partial_gating_seed3/final_model/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/llama32_modified/ablation_partial_gating_seed3/latest/expert_pools.pt | Other | 64.5 MB | 75cc0ceda86c |
| legacy/llama32_modified/ablation_partial_gating_seed3/latest/gated_lora_config.pt | Other | 1.8 KB | 373356a9eaef |
| legacy/llama32_modified/ablation_partial_gating_seed3/latest/gating_network.pt | Other | 49.0 MB | ad33cf380355 |
| legacy/llama32_modified/ablation_partial_gating_seed3/latest/scheduler.pt | Other | 1.7 KB | 3166389b2e94 |
| legacy/llama32_modified/ablation_partial_gating_seed3/visualizations/ablation_partial_gating_seed3_entropy_per_layer.png | Other | 41.6 KB | 31995fa9eb34 |
| legacy/llama32_modified/ablation_partial_gating_seed3/visualizations/ablation_partial_gating_seed3_layer_expert_heatmap.png | Other | 107.2 KB | 042ec209b3a2 |
| legacy/llama32_modified/ablation_partial_gating_seed3/visualizations/ablation_partial_gating_seed3_task_expert_usage.png | Other | 41.6 KB | 783688a97887 |
| legacy/llama32_modified/ablation_partial_gating_seed3/visualizations/ablation_partial_gating_seed3_token_routing_1.png | Other | 96.4 KB | 36364f2c3c3c |
| legacy/llama32_modified/ablation_partial_gating_seed3/visualizations/ablation_partial_gating_seed3_token_routing_2.png | Other | 96.7 KB | 01dbda95a91a |
| legacy/llama32_modified/ablation_partial_gating_seed3/visualizations/ablation_partial_gating_seed3_token_routing_3.png | Other | 96.8 KB | f3d322aec1eb |
| legacy/llama32_modified/exp2_gated_2experts_seed1/TRAINING_DONE | Other | 111 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed1/best_model/expert_pools.pt | Other | 27.7 MB | 68dcb5068983 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/best_model/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/best_model/gating_network.pt | Other | 49.0 MB | 612c16792039 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/best_model/scheduler.pt | Other | 1.7 KB | 482234865e56 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-1000/expert_pools.pt | Other | 27.7 MB | 5b27a6ce58da |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-1000/gating_network.pt | Other | 49.0 MB | 23e0691315cd |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 75d0483a00c8 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-1500/expert_pools.pt | Other | 27.7 MB | 751b52abc6b1 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-1500/gating_network.pt | Other | 49.0 MB | 7fd53d4b5283 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-1500/scheduler.pt | Other | 1.7 KB | a930f4a734fe |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-2000/expert_pools.pt | Other | 27.7 MB | 1e08fccc9995 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-2000/gating_network.pt | Other | 49.0 MB | ae4a12573bb7 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-2000/scheduler.pt | Other | 1.7 KB | b5ded2205a43 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-2500/expert_pools.pt | Other | 27.7 MB | 68c2d0f4da9d |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-2500/gating_network.pt | Other | 49.0 MB | e1c0539f106c |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 8edb16e6cc0f |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-3000/expert_pools.pt | Other | 27.7 MB | 014eb87d19d0 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-3000/gating_network.pt | Other | 49.0 MB | eec0e2bd60fc |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 438e7c9aba3b |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-3500/expert_pools.pt | Other | 27.7 MB | 44d866f4034d |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-3500/gating_network.pt | Other | 49.0 MB | a5d44c8e4693 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 82a86129150c |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-4000/expert_pools.pt | Other | 27.7 MB | 2dfb783e352d |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-4000/gating_network.pt | Other | 49.0 MB | 42b1158ff132 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 9793afb9d64c |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-500/expert_pools.pt | Other | 27.7 MB | 7aa71506349c |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-500/gating_network.pt | Other | 49.0 MB | fcc25276ae93 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/checkpoint-500/scheduler.pt | Other | 1.7 KB | d2c4f1faa352 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/epoch-1/expert_pools.pt | Other | 27.7 MB | d7ef918b7104 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/epoch-1/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/epoch-1/gating_network.pt | Other | 49.0 MB | 384c2a80687d |
| legacy/llama32_modified/exp2_gated_2experts_seed1/epoch-1/scheduler.pt | Other | 1.7 KB | 86f6731f97de |
| legacy/llama32_modified/exp2_gated_2experts_seed1/epoch-2/expert_pools.pt | Other | 27.7 MB | b2c7d4f6fde1 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/epoch-2/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/epoch-2/gating_network.pt | Other | 49.0 MB | 0bba864f9995 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/epoch-2/scheduler.pt | Other | 1.7 KB | 61c7ee9cc021 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/epoch-3/expert_pools.pt | Other | 27.7 MB | 3dd220757191 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/epoch-3/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/epoch-3/gating_network.pt | Other | 49.0 MB | 723a0e2a8333 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/epoch-3/scheduler.pt | Other | 1.7 KB | 3166389b2e94 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/epoch-4/expert_pools.pt | Other | 27.7 MB | 22ec89144a10 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/epoch-4/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/epoch-4/gating_network.pt | Other | 49.0 MB | a15991ad8bc8 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/epoch-4/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/final_model/expert_pools.pt | Other | 27.7 MB | 22ec89144a10 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/final_model/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/final_model/gating_network.pt | Other | 49.0 MB | a15991ad8bc8 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/final_model/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/latest/expert_pools.pt | Other | 27.7 MB | 6b4c0b948733 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/latest/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/latest/gating_network.pt | Other | 49.0 MB | 0df454d5dc5e |
| legacy/llama32_modified/exp2_gated_2experts_seed1/latest/scheduler.pt | Other | 1.7 KB | 1eb2f65e818e |
| legacy/llama32_modified/exp2_gated_2experts_seed1/visualizations/exp2_gated_2experts_seed1_entropy_per_layer.png | Other | 43.5 KB | fb5fe9ac18dc |
| legacy/llama32_modified/exp2_gated_2experts_seed1/visualizations/exp2_gated_2experts_seed1_layer_expert_heatmap.png | Other | 107.0 KB | 20bc3d7aac62 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/visualizations/exp2_gated_2experts_seed1_task_expert_usage.png | Other | 39.9 KB | 51a266564ab5 |
| legacy/llama32_modified/exp2_gated_2experts_seed1/visualizations/exp2_gated_2experts_seed1_token_routing_1.png | Other | 98.0 KB | ec77fad11c5a |
| legacy/llama32_modified/exp2_gated_2experts_seed1/visualizations/exp2_gated_2experts_seed1_token_routing_2.png | Other | 97.8 KB | 92481163ec0e |
| legacy/llama32_modified/exp2_gated_2experts_seed1/visualizations/exp2_gated_2experts_seed1_token_routing_3.png | Other | 98.3 KB | 3c3160e5940a |
| legacy/llama32_modified/exp2_gated_2experts_seed2/TRAINING_DONE | Other | 110 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed2/best_model/expert_pools.pt | Other | 27.7 MB | bf7dfe3c1c8b |
| legacy/llama32_modified/exp2_gated_2experts_seed2/best_model/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/best_model/gating_network.pt | Other | 49.0 MB | e5a131e98f69 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/best_model/scheduler.pt | Other | 1.7 KB | df9d6a6f0d6d |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-1000/expert_pools.pt | Other | 27.7 MB | 01e7d2fd2ab5 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-1000/gating_network.pt | Other | 49.0 MB | 38dc33fbd2f9 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 75d0483a00c8 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-1500/expert_pools.pt | Other | 27.7 MB | 428aa1096c4e |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-1500/gating_network.pt | Other | 49.0 MB | 883299405121 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-1500/scheduler.pt | Other | 1.7 KB | a930f4a734fe |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-2000/expert_pools.pt | Other | 27.7 MB | f46569546a9b |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-2000/gating_network.pt | Other | 49.0 MB | 536de9c38766 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-2000/scheduler.pt | Other | 1.7 KB | b5ded2205a43 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-2500/expert_pools.pt | Other | 27.7 MB | 473b61d8efa9 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-2500/gating_network.pt | Other | 49.0 MB | 3edf308b8a85 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 8edb16e6cc0f |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-3000/expert_pools.pt | Other | 27.7 MB | 6c0bee0f9309 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-3000/gating_network.pt | Other | 49.0 MB | f17e00a1442d |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 438e7c9aba3b |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-3500/expert_pools.pt | Other | 27.7 MB | 20fe3633a1ff |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-3500/gating_network.pt | Other | 49.0 MB | c19064542048 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 82a86129150c |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-4000/expert_pools.pt | Other | 27.7 MB | fffda47da5a1 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-4000/gating_network.pt | Other | 49.0 MB | 93feb4387174 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 9793afb9d64c |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-500/expert_pools.pt | Other | 27.7 MB | 2322c5d0e00e |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-500/gating_network.pt | Other | 49.0 MB | b4b354b9b23a |
| legacy/llama32_modified/exp2_gated_2experts_seed2/checkpoint-500/scheduler.pt | Other | 1.7 KB | d2c4f1faa352 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/epoch-1/expert_pools.pt | Other | 27.7 MB | e89b203b58d5 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/epoch-1/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/epoch-1/gating_network.pt | Other | 49.0 MB | 8d62e7bf3bda |
| legacy/llama32_modified/exp2_gated_2experts_seed2/epoch-1/scheduler.pt | Other | 1.7 KB | 86f6731f97de |
| legacy/llama32_modified/exp2_gated_2experts_seed2/epoch-2/expert_pools.pt | Other | 27.7 MB | 5f750bafba2b |
| legacy/llama32_modified/exp2_gated_2experts_seed2/epoch-2/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/epoch-2/gating_network.pt | Other | 49.0 MB | b8eeff2bb986 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/epoch-2/scheduler.pt | Other | 1.7 KB | 61c7ee9cc021 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/epoch-3/expert_pools.pt | Other | 27.7 MB | b64ab3036055 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/epoch-3/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/epoch-3/gating_network.pt | Other | 49.0 MB | 46503e4e473e |
| legacy/llama32_modified/exp2_gated_2experts_seed2/epoch-3/scheduler.pt | Other | 1.7 KB | 3166389b2e94 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/epoch-4/expert_pools.pt | Other | 27.7 MB | 6ff8d8f73dfa |
| legacy/llama32_modified/exp2_gated_2experts_seed2/epoch-4/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/epoch-4/gating_network.pt | Other | 49.0 MB | 1eb2e1d7587c |
| legacy/llama32_modified/exp2_gated_2experts_seed2/epoch-4/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/final_model/expert_pools.pt | Other | 27.7 MB | 6ff8d8f73dfa |
| legacy/llama32_modified/exp2_gated_2experts_seed2/final_model/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/final_model/gating_network.pt | Other | 49.0 MB | 1eb2e1d7587c |
| legacy/llama32_modified/exp2_gated_2experts_seed2/final_model/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/latest/expert_pools.pt | Other | 27.7 MB | 3e73a78206ae |
| legacy/llama32_modified/exp2_gated_2experts_seed2/latest/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/latest/gating_network.pt | Other | 49.0 MB | 64fea131ad94 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/latest/scheduler.pt | Other | 1.7 KB | c303bbee1321 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/visualizations/exp2_gated_2experts_seed2_entropy_per_layer.png | Other | 43.1 KB | 8d90a1b35103 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/visualizations/exp2_gated_2experts_seed2_layer_expert_heatmap.png | Other | 105.8 KB | 94b7fd243ee3 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/visualizations/exp2_gated_2experts_seed2_task_expert_usage.png | Other | 39.7 KB | 811cdca60071 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/visualizations/exp2_gated_2experts_seed2_token_routing_1.png | Other | 96.6 KB | d170cfc114fb |
| legacy/llama32_modified/exp2_gated_2experts_seed2/visualizations/exp2_gated_2experts_seed2_token_routing_2.png | Other | 96.7 KB | 16a6c64e06f2 |
| legacy/llama32_modified/exp2_gated_2experts_seed2/visualizations/exp2_gated_2experts_seed2_token_routing_3.png | Other | 96.9 KB | 8b58f8593b37 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/TRAINING_DONE | Other | 111 B | — |
| legacy/llama32_modified/exp2_gated_2experts_seed3/best_model/expert_pools.pt | Other | 27.7 MB | 05f2b9f4331e |
| legacy/llama32_modified/exp2_gated_2experts_seed3/best_model/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/best_model/gating_network.pt | Other | 49.0 MB | d858fcb09456 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/best_model/scheduler.pt | Other | 1.7 KB | 482234865e56 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-1000/expert_pools.pt | Other | 27.7 MB | 9644d5acdf64 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-1000/gating_network.pt | Other | 49.0 MB | 8ff7716857ae |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 75d0483a00c8 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-1500/expert_pools.pt | Other | 27.7 MB | 427b2f885e9d |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-1500/gating_network.pt | Other | 49.0 MB | 219aadd1e643 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-1500/scheduler.pt | Other | 1.7 KB | a930f4a734fe |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-2000/expert_pools.pt | Other | 27.7 MB | ea6c94c135e6 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-2000/gating_network.pt | Other | 49.0 MB | dc0b14abfd9f |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-2000/scheduler.pt | Other | 1.7 KB | b5ded2205a43 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-2500/expert_pools.pt | Other | 27.7 MB | 644084e5a58c |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-2500/gating_network.pt | Other | 49.0 MB | 73bfd6d8dc0f |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 8edb16e6cc0f |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-3000/expert_pools.pt | Other | 27.7 MB | da308a13d5f9 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-3000/gating_network.pt | Other | 49.0 MB | cbf34078ed98 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 438e7c9aba3b |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-3500/expert_pools.pt | Other | 27.7 MB | 7520e294223b |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-3500/gating_network.pt | Other | 49.0 MB | 527aad39cc39 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 82a86129150c |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-4000/expert_pools.pt | Other | 27.7 MB | d54a502143d1 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-4000/gating_network.pt | Other | 49.0 MB | 2a0bb7cb38fb |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 9793afb9d64c |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-500/expert_pools.pt | Other | 27.7 MB | 92a00a5bb5ba |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-500/gating_network.pt | Other | 49.0 MB | 4cad327b00e1 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/checkpoint-500/scheduler.pt | Other | 1.7 KB | d2c4f1faa352 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/epoch-1/expert_pools.pt | Other | 27.7 MB | e45880e27526 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/epoch-1/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/epoch-1/gating_network.pt | Other | 49.0 MB | fb22fc2e55e7 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/epoch-1/scheduler.pt | Other | 1.7 KB | 86f6731f97de |
| legacy/llama32_modified/exp2_gated_2experts_seed3/epoch-2/expert_pools.pt | Other | 27.7 MB | 94db359faa64 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/epoch-2/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/epoch-2/gating_network.pt | Other | 49.0 MB | c5c4660d015a |
| legacy/llama32_modified/exp2_gated_2experts_seed3/epoch-2/scheduler.pt | Other | 1.7 KB | 61c7ee9cc021 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/epoch-3/expert_pools.pt | Other | 27.7 MB | b58ab9512485 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/epoch-3/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/epoch-3/gating_network.pt | Other | 49.0 MB | c0edc0644d97 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/epoch-3/scheduler.pt | Other | 1.7 KB | 3166389b2e94 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/epoch-4/expert_pools.pt | Other | 27.7 MB | bea6bbbca420 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/epoch-4/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/epoch-4/gating_network.pt | Other | 49.0 MB | da692011734b |
| legacy/llama32_modified/exp2_gated_2experts_seed3/epoch-4/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/final_model/expert_pools.pt | Other | 27.7 MB | bea6bbbca420 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/final_model/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/final_model/gating_network.pt | Other | 49.0 MB | da692011734b |
| legacy/llama32_modified/exp2_gated_2experts_seed3/final_model/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/latest/expert_pools.pt | Other | 27.7 MB | 895a8e09cdbe |
| legacy/llama32_modified/exp2_gated_2experts_seed3/latest/gated_lora_config.pt | Other | 1.8 KB | 6404870bed52 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/latest/gating_network.pt | Other | 49.0 MB | 33b42fabff87 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/latest/scheduler.pt | Other | 1.7 KB | fe1ed971b14a |
| legacy/llama32_modified/exp2_gated_2experts_seed3/visualizations/exp2_gated_2experts_seed3_entropy_per_layer.png | Other | 43.5 KB | 0b3bb7d0aeaa |
| legacy/llama32_modified/exp2_gated_2experts_seed3/visualizations/exp2_gated_2experts_seed3_layer_expert_heatmap.png | Other | 107.3 KB | f9db93fd57d7 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/visualizations/exp2_gated_2experts_seed3_task_expert_usage.png | Other | 39.5 KB | b535bee9f4ae |
| legacy/llama32_modified/exp2_gated_2experts_seed3/visualizations/exp2_gated_2experts_seed3_token_routing_1.png | Other | 97.0 KB | b65e5280890a |
| legacy/llama32_modified/exp2_gated_2experts_seed3/visualizations/exp2_gated_2experts_seed3_token_routing_2.png | Other | 96.8 KB | 42b676735ed0 |
| legacy/llama32_modified/exp2_gated_2experts_seed3/visualizations/exp2_gated_2experts_seed3_token_routing_3.png | Other | 97.2 KB | 6464761e688a |
| legacy/llama32_modified/exp3_gated_3experts_seed1/TRAINING_DONE | Other | 110 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed1/best_model/expert_pools.pt | Other | 64.5 MB | b727961601fc |
| legacy/llama32_modified/exp3_gated_3experts_seed1/best_model/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/best_model/gating_network.pt | Other | 49.0 MB | c7cc6aea64f7 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/best_model/scheduler.pt | Other | 1.7 KB | 8a283b73661c |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-1000/expert_pools.pt | Other | 64.5 MB | b9d65c55b89c |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-1000/gating_network.pt | Other | 49.0 MB | afaa2ac3fa8b |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 75d0483a00c8 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-1500/expert_pools.pt | Other | 64.5 MB | 65ed617ed723 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-1500/gating_network.pt | Other | 49.0 MB | 572f0cfa2039 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-1500/scheduler.pt | Other | 1.7 KB | a930f4a734fe |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-2000/expert_pools.pt | Other | 64.5 MB | 57c42fdd2081 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-2000/gating_network.pt | Other | 49.0 MB | c0252b88b7f4 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-2000/scheduler.pt | Other | 1.7 KB | b5ded2205a43 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-2500/expert_pools.pt | Other | 64.5 MB | 8e7f86335718 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-2500/gating_network.pt | Other | 49.0 MB | 9c4181e450a3 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 8edb16e6cc0f |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-3000/expert_pools.pt | Other | 64.5 MB | 7e7c0ea06f73 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-3000/gating_network.pt | Other | 49.0 MB | bd0b63eccea5 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 438e7c9aba3b |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-3500/expert_pools.pt | Other | 64.5 MB | 854136fc31c4 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-3500/gating_network.pt | Other | 49.0 MB | 5c57aa5c480b |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 82a86129150c |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-4000/expert_pools.pt | Other | 64.5 MB | 4775301ccb00 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-4000/gating_network.pt | Other | 49.0 MB | 5a7d8a0bed11 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 9793afb9d64c |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-500/expert_pools.pt | Other | 64.5 MB | cb161f9e1879 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-500/gating_network.pt | Other | 49.0 MB | 25b895ab4442 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/checkpoint-500/scheduler.pt | Other | 1.7 KB | d2c4f1faa352 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/epoch-1/expert_pools.pt | Other | 64.5 MB | 4d387e2140b1 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/epoch-1/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/epoch-1/gating_network.pt | Other | 49.0 MB | 7731f46ea40c |
| legacy/llama32_modified/exp3_gated_3experts_seed1/epoch-1/scheduler.pt | Other | 1.7 KB | 86f6731f97de |
| legacy/llama32_modified/exp3_gated_3experts_seed1/epoch-2/expert_pools.pt | Other | 64.5 MB | 6b9e20e267b6 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/epoch-2/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/epoch-2/gating_network.pt | Other | 49.0 MB | 3d0b38d7943f |
| legacy/llama32_modified/exp3_gated_3experts_seed1/epoch-2/scheduler.pt | Other | 1.7 KB | 61c7ee9cc021 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/epoch-3/expert_pools.pt | Other | 64.5 MB | b3db4ac7bff9 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/epoch-3/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/epoch-3/gating_network.pt | Other | 49.0 MB | f748a4af4967 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/epoch-3/scheduler.pt | Other | 1.7 KB | 3166389b2e94 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/epoch-4/expert_pools.pt | Other | 64.5 MB | d090ef1bfbde |
| legacy/llama32_modified/exp3_gated_3experts_seed1/epoch-4/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/epoch-4/gating_network.pt | Other | 49.0 MB | c9ec16c9ab5b |
| legacy/llama32_modified/exp3_gated_3experts_seed1/epoch-4/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/final_model/expert_pools.pt | Other | 64.5 MB | d090ef1bfbde |
| legacy/llama32_modified/exp3_gated_3experts_seed1/final_model/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/final_model/gating_network.pt | Other | 49.0 MB | c9ec16c9ab5b |
| legacy/llama32_modified/exp3_gated_3experts_seed1/final_model/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/latest/expert_pools.pt | Other | 64.5 MB | 9a8d68f5b09e |
| legacy/llama32_modified/exp3_gated_3experts_seed1/latest/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/latest/gating_network.pt | Other | 49.0 MB | 8a82fb5156be |
| legacy/llama32_modified/exp3_gated_3experts_seed1/latest/scheduler.pt | Other | 1.7 KB | 47244d889136 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/visualizations/exp3_gated_3experts_seed1_entropy_per_layer.png | Other | 43.0 KB | 867846d119f7 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/visualizations/exp3_gated_3experts_seed1_layer_expert_heatmap.png | Other | 109.5 KB | d931ffda1f17 |
| legacy/llama32_modified/exp3_gated_3experts_seed1/visualizations/exp3_gated_3experts_seed1_task_expert_usage.png | Other | 38.0 KB | 96b6fb38d5af |
| legacy/llama32_modified/exp3_gated_3experts_seed1/visualizations/exp3_gated_3experts_seed1_token_routing_1.png | Other | 101.4 KB | 46c1ca26ef2c |
| legacy/llama32_modified/exp3_gated_3experts_seed1/visualizations/exp3_gated_3experts_seed1_token_routing_2.png | Other | 101.6 KB | 2f61c5f2826e |
| legacy/llama32_modified/exp3_gated_3experts_seed1/visualizations/exp3_gated_3experts_seed1_token_routing_3.png | Other | 101.6 KB | 9cc38c5ab248 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/TRAINING_DONE | Other | 111 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed2/best_model/expert_pools.pt | Other | 64.5 MB | 6daf6e648c3e |
| legacy/llama32_modified/exp3_gated_3experts_seed2/best_model/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/best_model/gating_network.pt | Other | 49.0 MB | 2ce230a0646f |
| legacy/llama32_modified/exp3_gated_3experts_seed2/best_model/scheduler.pt | Other | 1.7 KB | 42a3ddb1d5d9 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-1000/expert_pools.pt | Other | 64.5 MB | ac44c97badbf |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-1000/gating_network.pt | Other | 49.0 MB | 52210edc8262 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 75d0483a00c8 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-1500/expert_pools.pt | Other | 64.5 MB | 47e08504d44e |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-1500/gating_network.pt | Other | 49.0 MB | b6e18928d6f9 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-1500/scheduler.pt | Other | 1.7 KB | a930f4a734fe |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-2000/expert_pools.pt | Other | 64.5 MB | 39e5fe48bd68 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-2000/gating_network.pt | Other | 49.0 MB | 68fb292d295c |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-2000/scheduler.pt | Other | 1.7 KB | b5ded2205a43 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-2500/expert_pools.pt | Other | 64.5 MB | 202d1d722044 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-2500/gating_network.pt | Other | 49.0 MB | 84dc16cb3580 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 8edb16e6cc0f |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-3000/expert_pools.pt | Other | 64.5 MB | 433d6d13c401 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-3000/gating_network.pt | Other | 49.0 MB | 6b9d662a753a |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 438e7c9aba3b |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-3500/expert_pools.pt | Other | 64.5 MB | 5897fa8e2cca |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-3500/gating_network.pt | Other | 49.0 MB | 91de3a3f208c |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 82a86129150c |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-4000/expert_pools.pt | Other | 64.5 MB | d01a00bf8f22 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-4000/gating_network.pt | Other | 49.0 MB | 4b771ee0373e |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 9793afb9d64c |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-500/expert_pools.pt | Other | 64.5 MB | a5645fbef855 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-500/gating_network.pt | Other | 49.0 MB | 4b301ce39bf2 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/checkpoint-500/scheduler.pt | Other | 1.7 KB | d2c4f1faa352 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/epoch-1/expert_pools.pt | Other | 64.5 MB | 8be389f8b97b |
| legacy/llama32_modified/exp3_gated_3experts_seed2/epoch-1/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/epoch-1/gating_network.pt | Other | 49.0 MB | 65ab05a71d7a |
| legacy/llama32_modified/exp3_gated_3experts_seed2/epoch-1/scheduler.pt | Other | 1.7 KB | 86f6731f97de |
| legacy/llama32_modified/exp3_gated_3experts_seed2/epoch-2/expert_pools.pt | Other | 64.5 MB | 69647f7f6680 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/epoch-2/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/epoch-2/gating_network.pt | Other | 49.0 MB | 8e2a7f70bf68 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/epoch-2/scheduler.pt | Other | 1.7 KB | 61c7ee9cc021 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/epoch-3/expert_pools.pt | Other | 64.5 MB | e8e8e241977a |
| legacy/llama32_modified/exp3_gated_3experts_seed2/epoch-3/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/epoch-3/gating_network.pt | Other | 49.0 MB | 03188a8f743b |
| legacy/llama32_modified/exp3_gated_3experts_seed2/epoch-3/scheduler.pt | Other | 1.7 KB | 3166389b2e94 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/epoch-4/expert_pools.pt | Other | 64.5 MB | dcd83c72ddc1 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/epoch-4/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/epoch-4/gating_network.pt | Other | 49.0 MB | 260a51a53000 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/epoch-4/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/final_model/expert_pools.pt | Other | 64.5 MB | dcd83c72ddc1 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/final_model/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/final_model/gating_network.pt | Other | 49.0 MB | 260a51a53000 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/final_model/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/latest/expert_pools.pt | Other | 64.5 MB | 1dea69a268e9 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/latest/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/latest/gating_network.pt | Other | 49.0 MB | e5610f06f0fc |
| legacy/llama32_modified/exp3_gated_3experts_seed2/latest/scheduler.pt | Other | 1.7 KB | 1ba100b8fd7e |
| legacy/llama32_modified/exp3_gated_3experts_seed2/visualizations/exp3_gated_3experts_seed2_entropy_per_layer.png | Other | 42.7 KB | 3afa7b2eeee4 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/visualizations/exp3_gated_3experts_seed2_layer_expert_heatmap.png | Other | 110.0 KB | 089ef87035ad |
| legacy/llama32_modified/exp3_gated_3experts_seed2/visualizations/exp3_gated_3experts_seed2_task_expert_usage.png | Other | 39.2 KB | ef8135ca29c0 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/visualizations/exp3_gated_3experts_seed2_token_routing_1.png | Other | 99.3 KB | 78ce16f8fede |
| legacy/llama32_modified/exp3_gated_3experts_seed2/visualizations/exp3_gated_3experts_seed2_token_routing_2.png | Other | 99.4 KB | 945a7afd6329 |
| legacy/llama32_modified/exp3_gated_3experts_seed2/visualizations/exp3_gated_3experts_seed2_token_routing_3.png | Other | 99.2 KB | d73a7cd61ab8 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/TRAINING_DONE | Other | 111 B | — |
| legacy/llama32_modified/exp3_gated_3experts_seed3/best_model/expert_pools.pt | Other | 64.5 MB | 333fc4c1a453 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/best_model/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/best_model/gating_network.pt | Other | 49.0 MB | 8392bfafd37c |
| legacy/llama32_modified/exp3_gated_3experts_seed3/best_model/scheduler.pt | Other | 1.7 KB | df9d6a6f0d6d |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-1000/expert_pools.pt | Other | 64.5 MB | b711d0710794 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-1000/gating_network.pt | Other | 49.0 MB | b00b2c2f0cc8 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 75d0483a00c8 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-1500/expert_pools.pt | Other | 64.5 MB | 11d480b984db |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-1500/gating_network.pt | Other | 49.0 MB | 5d1931059148 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-1500/scheduler.pt | Other | 1.7 KB | a930f4a734fe |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-2000/expert_pools.pt | Other | 64.5 MB | 1e2393040cad |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-2000/gating_network.pt | Other | 49.0 MB | db6674e0d77e |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-2000/scheduler.pt | Other | 1.7 KB | b5ded2205a43 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-2500/expert_pools.pt | Other | 64.5 MB | 33788dc0aa2a |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-2500/gating_network.pt | Other | 49.0 MB | 3540cbc818f7 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 8edb16e6cc0f |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-3000/expert_pools.pt | Other | 64.5 MB | 677c0e88f54b |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-3000/gating_network.pt | Other | 49.0 MB | 5db82b18deae |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 438e7c9aba3b |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-3500/expert_pools.pt | Other | 64.5 MB | 23c228a5d689 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-3500/gating_network.pt | Other | 49.0 MB | 8b9bfa12e64a |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 82a86129150c |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-4000/expert_pools.pt | Other | 64.5 MB | 851a6e7338f8 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-4000/gating_network.pt | Other | 49.0 MB | 688f9dfd7bbd |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 9793afb9d64c |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-500/expert_pools.pt | Other | 64.5 MB | 27ea8f202631 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-500/gating_network.pt | Other | 49.0 MB | da799a696ee7 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/checkpoint-500/scheduler.pt | Other | 1.7 KB | d2c4f1faa352 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/epoch-1/expert_pools.pt | Other | 64.5 MB | 33da064be2b8 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/epoch-1/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/epoch-1/gating_network.pt | Other | 49.0 MB | f5c2993d9792 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/epoch-1/scheduler.pt | Other | 1.7 KB | 86f6731f97de |
| legacy/llama32_modified/exp3_gated_3experts_seed3/epoch-2/expert_pools.pt | Other | 64.5 MB | 2bd4e6205aa7 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/epoch-2/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/epoch-2/gating_network.pt | Other | 49.0 MB | 0281c6e88ec7 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/epoch-2/scheduler.pt | Other | 1.7 KB | 61c7ee9cc021 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/epoch-3/expert_pools.pt | Other | 64.5 MB | 75d6bd6ec2b5 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/epoch-3/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/epoch-3/gating_network.pt | Other | 49.0 MB | bd4ca5610075 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/epoch-3/scheduler.pt | Other | 1.7 KB | 3166389b2e94 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/epoch-4/expert_pools.pt | Other | 64.5 MB | e74fffefd2e7 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/epoch-4/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/epoch-4/gating_network.pt | Other | 49.0 MB | dda2f1d92362 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/epoch-4/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/final_model/expert_pools.pt | Other | 64.5 MB | e74fffefd2e7 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/final_model/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/final_model/gating_network.pt | Other | 49.0 MB | dda2f1d92362 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/final_model/scheduler.pt | Other | 1.7 KB | 445a69c8edd9 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/latest/expert_pools.pt | Other | 64.5 MB | 14f0186e558d |
| legacy/llama32_modified/exp3_gated_3experts_seed3/latest/gated_lora_config.pt | Other | 1.8 KB | fdec88aa9d99 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/latest/gating_network.pt | Other | 49.0 MB | a670e7645ec7 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/latest/scheduler.pt | Other | 1.7 KB | 47244d889136 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/visualizations/exp3_gated_3experts_seed3_entropy_per_layer.png | Other | 43.2 KB | 211c57019f33 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/visualizations/exp3_gated_3experts_seed3_layer_expert_heatmap.png | Other | 109.8 KB | 2db6bf80545d |
| legacy/llama32_modified/exp3_gated_3experts_seed3/visualizations/exp3_gated_3experts_seed3_task_expert_usage.png | Other | 38.4 KB | 204eb5e15946 |
| legacy/llama32_modified/exp3_gated_3experts_seed3/visualizations/exp3_gated_3experts_seed3_token_routing_1.png | Other | 98.2 KB | be1c6d503a7d |
| legacy/llama32_modified/exp3_gated_3experts_seed3/visualizations/exp3_gated_3experts_seed3_token_routing_2.png | Other | 98.5 KB | 9e0b491696ab |
| legacy/llama32_modified/exp3_gated_3experts_seed3/visualizations/exp3_gated_3experts_seed3_token_routing_3.png | Other | 98.5 KB | 73a6d26de6f8 |
| legacy/phi2_ablations/ablation_no_l1/best_model/expert_pools.pt | Other | 73.8 MB | 576076631be7 |
| legacy/phi2_ablations/ablation_no_l1/best_model/gated_lora_config.pt | Other | 1.7 KB | a4ad4a3913e8 |
| legacy/phi2_ablations/ablation_no_l1/best_model/gating_network.pt | Other | 47.3 MB | 6efbc0268a91 |
| legacy/phi2_ablations/ablation_no_l1/best_model/scheduler.pt | Other | 1.7 KB | d4b3c87afb92 |
| legacy/phi2_ablations/ablation_no_l1/checkpoint-1000/expert_pools.pt | Other | 73.8 MB | ca5e4e87c0d4 |
| legacy/phi2_ablations/ablation_no_l1/checkpoint-1000/gated_lora_config.pt | Other | 1.7 KB | a4ad4a3913e8 |
| legacy/phi2_ablations/ablation_no_l1/checkpoint-1000/gating_network.pt | Other | 47.3 MB | 73e58b148c40 |
| legacy/phi2_ablations/ablation_no_l1/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 9402f83b5cfc |
| legacy/phi2_ablations/ablation_no_l1/checkpoint-1500/expert_pools.pt | Other | 73.8 MB | b04d1a738f37 |
| legacy/phi2_ablations/ablation_no_l1/checkpoint-1500/gated_lora_config.pt | Other | 1.7 KB | a4ad4a3913e8 |
| legacy/phi2_ablations/ablation_no_l1/checkpoint-1500/gating_network.pt | Other | 47.3 MB | 31e05fbd81de |
| legacy/phi2_ablations/ablation_no_l1/checkpoint-1500/scheduler.pt | Other | 1.7 KB | 70f9dc0166fe |
| legacy/phi2_ablations/ablation_no_l1/checkpoint-2000/expert_pools.pt | Other | 73.8 MB | 48155925d514 |
| legacy/phi2_ablations/ablation_no_l1/checkpoint-2000/gated_lora_config.pt | Other | 1.7 KB | a4ad4a3913e8 |
| legacy/phi2_ablations/ablation_no_l1/checkpoint-2000/gating_network.pt | Other | 47.3 MB | bac671736f62 |
| legacy/phi2_ablations/ablation_no_l1/checkpoint-2000/scheduler.pt | Other | 1.7 KB | 7a98b29dc045 |
| legacy/phi2_ablations/ablation_no_l1/checkpoint-2500/expert_pools.pt | Other | 73.8 MB | 576076631be7 |
| legacy/phi2_ablations/ablation_no_l1/checkpoint-2500/gated_lora_config.pt | Other | 1.7 KB | a4ad4a3913e8 |
| legacy/phi2_ablations/ablation_no_l1/checkpoint-2500/gating_network.pt | Other | 47.3 MB | 6efbc0268a91 |
| legacy/phi2_ablations/ablation_no_l1/checkpoint-2500/scheduler.pt | Other | 1.7 KB | d4b3c87afb92 |
| legacy/phi2_ablations/ablation_no_l1/checkpoint-500/expert_pools.pt | Other | 73.8 MB | 949082f2099e |
| legacy/phi2_ablations/ablation_no_l1/checkpoint-500/gated_lora_config.pt | Other | 1.7 KB | a4ad4a3913e8 |
| legacy/phi2_ablations/ablation_no_l1/checkpoint-500/gating_network.pt | Other | 47.3 MB | 0fe5c8b38fcf |
| legacy/phi2_ablations/ablation_no_l1/checkpoint-500/scheduler.pt | Other | 1.7 KB | a8e00d52a8c7 |
| legacy/phi2_ablations/ablation_no_l1/final_model/expert_pools.pt | Other | 73.8 MB | 576076631be7 |
| legacy/phi2_ablations/ablation_no_l1/final_model/gated_lora_config.pt | Other | 1.7 KB | a4ad4a3913e8 |
| legacy/phi2_ablations/ablation_no_l1/final_model/gating_network.pt | Other | 47.3 MB | 6efbc0268a91 |
| legacy/phi2_ablations/ablation_no_l1/final_model/scheduler.pt | Other | 1.7 KB | d4b3c87afb92 |
| legacy/phi2_ablations/ablation_no_l1/routing_analysis_v2/ablation_no_l1_entropy_per_layer.png | Other | 40.6 KB | 4f780667c66c |
| legacy/phi2_ablations/ablation_no_l1/routing_analysis_v2/ablation_no_l1_layer_expert_heatmap.png | Other | 65.7 KB | c08849f82770 |
| legacy/phi2_ablations/ablation_no_l1/routing_analysis_v2/ablation_no_l1_task_expert_usage.png | Other | 49.8 KB | f1faa7905d48 |
| legacy/phi2_ablations/ablation_no_l1/routing_analysis_v2/ablation_no_l1_token_routing_1.png | Other | 62.5 KB | 762621db1af6 |
| legacy/phi2_ablations/ablation_no_l1/routing_analysis_v2/ablation_no_l1_token_routing_2.png | Other | 84.1 KB | 7ac377071a44 |
| legacy/phi2_ablations/ablation_no_l1/routing_analysis_v2/ablation_no_l1_token_routing_3.png | Other | 93.4 KB | 004c02d8def8 |
| legacy/phi2_ablations/ablation_no_l1/visualizations/ablation_no_l1_entropy_per_layer.png | Other | 40.8 KB | d4d7199c4da0 |
| legacy/phi2_ablations/ablation_no_l1/visualizations/ablation_no_l1_layer_expert_heatmap.png | Other | 66.3 KB | 3c715f512027 |
| legacy/phi2_ablations/ablation_no_l1/visualizations/ablation_no_l1_task_expert_usage.png | Other | 39.2 KB | 52e43e643df1 |
| legacy/phi2_ablations/ablation_no_l1/visualizations/ablation_no_l1_token_routing_1.png | Other | 92.2 KB | 9979d4f3b796 |
| legacy/phi2_ablations/ablation_no_l1/visualizations/ablation_no_l1_token_routing_2.png | Other | 92.4 KB | 667f6ed33fbb |
| legacy/phi2_ablations/ablation_no_l1/visualizations/ablation_no_l1_token_routing_3.png | Other | 92.5 KB | b32ba5884241 |
| legacy/phi2_ablations/ablation_no_layer_emb/best_model/expert_pools.pt | Other | 73.8 MB | d5dda9d70af6 |
| legacy/phi2_ablations/ablation_no_layer_emb/best_model/gated_lora_config.pt | Other | 1.7 KB | 591a420bc862 |
| legacy/phi2_ablations/ablation_no_layer_emb/best_model/gating_network.pt | Other | 42.1 MB | 0ccc6204c3ab |
| legacy/phi2_ablations/ablation_no_layer_emb/best_model/scheduler.pt | Other | 1.7 KB | 317075d3824d |
| legacy/phi2_ablations/ablation_no_layer_emb/checkpoint-1000/expert_pools.pt | Other | 73.8 MB | 78d3597b4415 |
| legacy/phi2_ablations/ablation_no_layer_emb/checkpoint-1000/gated_lora_config.pt | Other | 1.7 KB | 591a420bc862 |
| legacy/phi2_ablations/ablation_no_layer_emb/checkpoint-1000/gating_network.pt | Other | 42.1 MB | a0b3e3561a25 |
| legacy/phi2_ablations/ablation_no_layer_emb/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 9402f83b5cfc |
| legacy/phi2_ablations/ablation_no_layer_emb/checkpoint-1500/expert_pools.pt | Other | 73.8 MB | 7089068087f0 |
| legacy/phi2_ablations/ablation_no_layer_emb/checkpoint-1500/gated_lora_config.pt | Other | 1.7 KB | 591a420bc862 |
| legacy/phi2_ablations/ablation_no_layer_emb/checkpoint-1500/gating_network.pt | Other | 42.1 MB | b90295ec9e71 |
| legacy/phi2_ablations/ablation_no_layer_emb/checkpoint-1500/scheduler.pt | Other | 1.7 KB | 70f9dc0166fe |
| legacy/phi2_ablations/ablation_no_layer_emb/checkpoint-2000/expert_pools.pt | Other | 73.8 MB | 89fa62a0e3e6 |
| legacy/phi2_ablations/ablation_no_layer_emb/checkpoint-2000/gated_lora_config.pt | Other | 1.7 KB | 591a420bc862 |
| legacy/phi2_ablations/ablation_no_layer_emb/checkpoint-2000/gating_network.pt | Other | 42.1 MB | 9b644c164469 |
| legacy/phi2_ablations/ablation_no_layer_emb/checkpoint-2000/scheduler.pt | Other | 1.7 KB | 7a98b29dc045 |
| legacy/phi2_ablations/ablation_no_layer_emb/checkpoint-2500/expert_pools.pt | Other | 73.8 MB | 962c93171cd3 |
| legacy/phi2_ablations/ablation_no_layer_emb/checkpoint-2500/gated_lora_config.pt | Other | 1.7 KB | 591a420bc862 |
| legacy/phi2_ablations/ablation_no_layer_emb/checkpoint-2500/gating_network.pt | Other | 42.1 MB | a09772230554 |
| legacy/phi2_ablations/ablation_no_layer_emb/checkpoint-2500/scheduler.pt | Other | 1.7 KB | d4b3c87afb92 |
| legacy/phi2_ablations/ablation_no_layer_emb/checkpoint-500/expert_pools.pt | Other | 73.8 MB | cff6fa359f9f |
| legacy/phi2_ablations/ablation_no_layer_emb/checkpoint-500/gated_lora_config.pt | Other | 1.7 KB | 591a420bc862 |
| legacy/phi2_ablations/ablation_no_layer_emb/checkpoint-500/gating_network.pt | Other | 42.1 MB | 9ba3752ba0f4 |
| legacy/phi2_ablations/ablation_no_layer_emb/checkpoint-500/scheduler.pt | Other | 1.7 KB | a8e00d52a8c7 |
| legacy/phi2_ablations/ablation_no_layer_emb/final_model/expert_pools.pt | Other | 73.8 MB | 962c93171cd3 |
| legacy/phi2_ablations/ablation_no_layer_emb/final_model/gated_lora_config.pt | Other | 1.7 KB | 591a420bc862 |
| legacy/phi2_ablations/ablation_no_layer_emb/final_model/gating_network.pt | Other | 42.1 MB | a09772230554 |
| legacy/phi2_ablations/ablation_no_layer_emb/final_model/scheduler.pt | Other | 1.7 KB | d4b3c87afb92 |
| legacy/phi2_ablations/ablation_no_layer_emb/routing_analysis_v2/ablation_no_layer_emb_entropy_per_layer.png | Other | 41.2 KB | 3f30eb730d91 |
| legacy/phi2_ablations/ablation_no_layer_emb/routing_analysis_v2/ablation_no_layer_emb_layer_expert_heatmap.png | Other | 71.4 KB | 08c31f909e1d |
| legacy/phi2_ablations/ablation_no_layer_emb/routing_analysis_v2/ablation_no_layer_emb_task_expert_usage.png | Other | 51.5 KB | 9f1961209361 |
| legacy/phi2_ablations/ablation_no_layer_emb/routing_analysis_v2/ablation_no_layer_emb_token_routing_1.png | Other | 99.0 KB | 877250e9fbca |
| legacy/phi2_ablations/ablation_no_layer_emb/routing_analysis_v2/ablation_no_layer_emb_token_routing_2.png | Other | 88.8 KB | acd593fae934 |
| legacy/phi2_ablations/ablation_no_layer_emb/routing_analysis_v2/ablation_no_layer_emb_token_routing_3.png | Other | 99.5 KB | 053bd07cfdea |
| legacy/phi2_ablations/ablation_no_layer_emb/visualizations/ablation_no_layer_emb_entropy_per_layer.png | Other | 41.1 KB | 586f8aa984af |
| legacy/phi2_ablations/ablation_no_layer_emb/visualizations/ablation_no_layer_emb_layer_expert_heatmap.png | Other | 67.5 KB | 5d392d365e83 |
| legacy/phi2_ablations/ablation_no_layer_emb/visualizations/ablation_no_layer_emb_task_expert_usage.png | Other | 40.8 KB | d7c1883154ee |
| legacy/phi2_ablations/ablation_no_layer_emb/visualizations/ablation_no_layer_emb_token_routing_1.png | Other | 93.8 KB | 497e36c83329 |
| legacy/phi2_ablations/ablation_no_layer_emb/visualizations/ablation_no_layer_emb_token_routing_2.png | Other | 94.0 KB | 153a5a46ce77 |
| legacy/phi2_ablations/ablation_no_layer_emb/visualizations/ablation_no_layer_emb_token_routing_3.png | Other | 94.1 KB | 0a4172a4095a |
| legacy/phi2_ablations/ablation_partial_gating/best_model/expert_pools.pt | Other | 73.8 MB | 421437ed88e5 |
| legacy/phi2_ablations/ablation_partial_gating/best_model/gated_lora_config.pt | Other | 1.7 KB | 591a420bc862 |
| legacy/phi2_ablations/ablation_partial_gating/best_model/gating_network.pt | Other | 47.3 MB | 625f93b434b5 |
| legacy/phi2_ablations/ablation_partial_gating/best_model/scheduler.pt | Other | 1.7 KB | 0d500e7c9080 |
| legacy/phi2_ablations/ablation_partial_gating/checkpoint-1000/expert_pools.pt | Other | 73.8 MB | 21608d54fa3a |
| legacy/phi2_ablations/ablation_partial_gating/checkpoint-1000/gated_lora_config.pt | Other | 1.7 KB | 591a420bc862 |
| legacy/phi2_ablations/ablation_partial_gating/checkpoint-1000/gating_network.pt | Other | 47.3 MB | 6c0c404ee2b5 |
| legacy/phi2_ablations/ablation_partial_gating/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 9402f83b5cfc |
| legacy/phi2_ablations/ablation_partial_gating/checkpoint-1500/expert_pools.pt | Other | 73.8 MB | 4467501aaa0c |
| legacy/phi2_ablations/ablation_partial_gating/checkpoint-1500/gated_lora_config.pt | Other | 1.7 KB | 591a420bc862 |
| legacy/phi2_ablations/ablation_partial_gating/checkpoint-1500/gating_network.pt | Other | 47.3 MB | d3c54c262276 |
| legacy/phi2_ablations/ablation_partial_gating/checkpoint-1500/scheduler.pt | Other | 1.7 KB | 70f9dc0166fe |
| legacy/phi2_ablations/ablation_partial_gating/checkpoint-2000/expert_pools.pt | Other | 73.8 MB | b3edae5c3e85 |
| legacy/phi2_ablations/ablation_partial_gating/checkpoint-2000/gated_lora_config.pt | Other | 1.7 KB | 591a420bc862 |
| legacy/phi2_ablations/ablation_partial_gating/checkpoint-2000/gating_network.pt | Other | 47.3 MB | aa863cb203f2 |
| legacy/phi2_ablations/ablation_partial_gating/checkpoint-2000/scheduler.pt | Other | 1.7 KB | 7a98b29dc045 |
| legacy/phi2_ablations/ablation_partial_gating/checkpoint-2500/expert_pools.pt | Other | 73.8 MB | 74c5b204441e |
| legacy/phi2_ablations/ablation_partial_gating/checkpoint-2500/gated_lora_config.pt | Other | 1.7 KB | 591a420bc862 |
| legacy/phi2_ablations/ablation_partial_gating/checkpoint-2500/gating_network.pt | Other | 47.3 MB | 4e8a8408aa42 |
| legacy/phi2_ablations/ablation_partial_gating/checkpoint-2500/scheduler.pt | Other | 1.7 KB | d4b3c87afb92 |
| legacy/phi2_ablations/ablation_partial_gating/checkpoint-500/expert_pools.pt | Other | 73.8 MB | fbbc1c16a395 |
| legacy/phi2_ablations/ablation_partial_gating/checkpoint-500/gated_lora_config.pt | Other | 1.7 KB | 591a420bc862 |
| legacy/phi2_ablations/ablation_partial_gating/checkpoint-500/gating_network.pt | Other | 47.3 MB | 1b75b8378c5e |
| legacy/phi2_ablations/ablation_partial_gating/checkpoint-500/scheduler.pt | Other | 1.7 KB | a8e00d52a8c7 |
| legacy/phi2_ablations/ablation_partial_gating/final_model/expert_pools.pt | Other | 73.8 MB | 74c5b204441e |
| legacy/phi2_ablations/ablation_partial_gating/final_model/gated_lora_config.pt | Other | 1.7 KB | 591a420bc862 |
| legacy/phi2_ablations/ablation_partial_gating/final_model/gating_network.pt | Other | 47.3 MB | 4e8a8408aa42 |
| legacy/phi2_ablations/ablation_partial_gating/final_model/scheduler.pt | Other | 1.7 KB | d4b3c87afb92 |
| legacy/phi2_ablations/ablation_partial_gating/routing_analysis_v2/ablation_partial_gating_entropy_per_layer.png | Other | 41.7 KB | 5954a0775f80 |
| legacy/phi2_ablations/ablation_partial_gating/routing_analysis_v2/ablation_partial_gating_layer_expert_heatmap.png | Other | 75.5 KB | 485fe6ec92fd |
| legacy/phi2_ablations/ablation_partial_gating/routing_analysis_v2/ablation_partial_gating_task_expert_usage.png | Other | 51.6 KB | f44c1ac0cb8d |
| legacy/phi2_ablations/ablation_partial_gating/routing_analysis_v2/ablation_partial_gating_token_routing_1.png | Other | 82.6 KB | 9ffce17e1005 |
| legacy/phi2_ablations/ablation_partial_gating/routing_analysis_v2/ablation_partial_gating_token_routing_2.png | Other | 66.4 KB | 0116013037bd |
| legacy/phi2_ablations/ablation_partial_gating/routing_analysis_v2/ablation_partial_gating_token_routing_3.png | Other | 85.7 KB | e7bf8468de80 |
| legacy/pythia410m/ablation_no_l1_seed1/best_model/expert_pools.pt | Other | 16.7 MB | cd2fe7a67eab |
| legacy/pythia410m/ablation_no_l1_seed1/best_model/gated_lora_config.pt | Other | 1.8 KB | ae84443ea0d8 |
| legacy/pythia410m/ablation_no_l1_seed1/best_model/gating_network.pt | Other | 13.9 MB | ba730cf1962c |
| legacy/pythia410m/ablation_no_l1_seed1/best_model/scheduler.pt | Other | 1.7 KB | b2e0d0974bd3 |
| legacy/pythia410m/ablation_no_l1_seed1/checkpoint-1000/expert_pools.pt | Other | 16.7 MB | bce4c4338aa7 |
| legacy/pythia410m/ablation_no_l1_seed1/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | ae84443ea0d8 |
| legacy/pythia410m/ablation_no_l1_seed1/checkpoint-1000/gating_network.pt | Other | 13.9 MB | 4be5f727acee |
| legacy/pythia410m/ablation_no_l1_seed1/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 0aea463251e0 |
| legacy/pythia410m/ablation_no_l1_seed1/checkpoint-1500/expert_pools.pt | Other | 16.7 MB | 72e0d1514d5e |
| legacy/pythia410m/ablation_no_l1_seed1/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | ae84443ea0d8 |
| legacy/pythia410m/ablation_no_l1_seed1/checkpoint-1500/gating_network.pt | Other | 13.9 MB | 6bd49e59ef0c |
| legacy/pythia410m/ablation_no_l1_seed1/checkpoint-1500/scheduler.pt | Other | 1.7 KB | ab65e3db4ba5 |
| legacy/pythia410m/ablation_no_l1_seed1/checkpoint-2000/expert_pools.pt | Other | 16.7 MB | 70ded6236f9d |
| legacy/pythia410m/ablation_no_l1_seed1/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | ae84443ea0d8 |
| legacy/pythia410m/ablation_no_l1_seed1/checkpoint-2000/gating_network.pt | Other | 13.9 MB | eeb096be017c |
| legacy/pythia410m/ablation_no_l1_seed1/checkpoint-2000/scheduler.pt | Other | 1.7 KB | 3b2455392db2 |
| legacy/pythia410m/ablation_no_l1_seed1/checkpoint-500/expert_pools.pt | Other | 16.7 MB | e1a4de457316 |
| legacy/pythia410m/ablation_no_l1_seed1/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | ae84443ea0d8 |
| legacy/pythia410m/ablation_no_l1_seed1/checkpoint-500/gating_network.pt | Other | 13.9 MB | 21d9e784622f |
| legacy/pythia410m/ablation_no_l1_seed1/checkpoint-500/scheduler.pt | Other | 1.7 KB | 66c01bf5fb42 |
| legacy/pythia410m/ablation_no_l1_seed2/best_model/expert_pools.pt | Other | 16.7 MB | 0fba91bbd4c6 |
| legacy/pythia410m/ablation_no_l1_seed2/best_model/gated_lora_config.pt | Other | 1.8 KB | ae84443ea0d8 |
| legacy/pythia410m/ablation_no_l1_seed2/best_model/gating_network.pt | Other | 13.9 MB | 18e3d532f18c |
| legacy/pythia410m/ablation_no_l1_seed2/best_model/scheduler.pt | Other | 1.7 KB | d5482a786682 |
| legacy/pythia410m/ablation_no_l1_seed2/checkpoint-1000/expert_pools.pt | Other | 16.7 MB | 54d3a947ce06 |
| legacy/pythia410m/ablation_no_l1_seed2/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | ae84443ea0d8 |
| legacy/pythia410m/ablation_no_l1_seed2/checkpoint-1000/gating_network.pt | Other | 13.9 MB | e4555e39a42d |
| legacy/pythia410m/ablation_no_l1_seed2/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 0aea463251e0 |
| legacy/pythia410m/ablation_no_l1_seed2/checkpoint-1500/expert_pools.pt | Other | 16.7 MB | cf216e2cb49f |
| legacy/pythia410m/ablation_no_l1_seed2/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | ae84443ea0d8 |
| legacy/pythia410m/ablation_no_l1_seed2/checkpoint-1500/gating_network.pt | Other | 13.9 MB | c3e65c780444 |
| legacy/pythia410m/ablation_no_l1_seed2/checkpoint-1500/scheduler.pt | Other | 1.7 KB | ab65e3db4ba5 |
| legacy/pythia410m/ablation_no_l1_seed2/checkpoint-2000/expert_pools.pt | Other | 16.7 MB | fb78b51078e6 |
| legacy/pythia410m/ablation_no_l1_seed2/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | ae84443ea0d8 |
| legacy/pythia410m/ablation_no_l1_seed2/checkpoint-2000/gating_network.pt | Other | 13.9 MB | f06784d1c00a |
| legacy/pythia410m/ablation_no_l1_seed2/checkpoint-2000/scheduler.pt | Other | 1.7 KB | 3b2455392db2 |
| legacy/pythia410m/ablation_no_l1_seed2/checkpoint-500/expert_pools.pt | Other | 16.7 MB | 1045f05f348f |
| legacy/pythia410m/ablation_no_l1_seed2/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | ae84443ea0d8 |
| legacy/pythia410m/ablation_no_l1_seed2/checkpoint-500/gating_network.pt | Other | 13.9 MB | e30e59d6e68d |
| legacy/pythia410m/ablation_no_l1_seed2/checkpoint-500/scheduler.pt | Other | 1.7 KB | 66c01bf5fb42 |
| legacy/pythia410m/ablation_no_l1_seed3/best_model/expert_pools.pt | Other | 16.7 MB | 4361bd08d6c0 |
| legacy/pythia410m/ablation_no_l1_seed3/best_model/gated_lora_config.pt | Other | 1.8 KB | ae84443ea0d8 |
| legacy/pythia410m/ablation_no_l1_seed3/best_model/gating_network.pt | Other | 13.9 MB | 96411f40200e |
| legacy/pythia410m/ablation_no_l1_seed3/best_model/scheduler.pt | Other | 1.7 KB | d5482a786682 |
| legacy/pythia410m/ablation_no_l1_seed3/checkpoint-1000/expert_pools.pt | Other | 16.7 MB | 534128c446d2 |
| legacy/pythia410m/ablation_no_l1_seed3/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | ae84443ea0d8 |
| legacy/pythia410m/ablation_no_l1_seed3/checkpoint-1000/gating_network.pt | Other | 13.9 MB | 36ac998252fb |
| legacy/pythia410m/ablation_no_l1_seed3/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 0aea463251e0 |
| legacy/pythia410m/ablation_no_l1_seed3/checkpoint-1500/expert_pools.pt | Other | 16.7 MB | 9a7019c83af1 |
| legacy/pythia410m/ablation_no_l1_seed3/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | ae84443ea0d8 |
| legacy/pythia410m/ablation_no_l1_seed3/checkpoint-1500/gating_network.pt | Other | 13.9 MB | 35e3d48902f9 |
| legacy/pythia410m/ablation_no_l1_seed3/checkpoint-1500/scheduler.pt | Other | 1.7 KB | ab65e3db4ba5 |
| legacy/pythia410m/ablation_no_l1_seed3/checkpoint-2000/expert_pools.pt | Other | 16.7 MB | c49923bd6b59 |
| legacy/pythia410m/ablation_no_l1_seed3/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | ae84443ea0d8 |
| legacy/pythia410m/ablation_no_l1_seed3/checkpoint-2000/gating_network.pt | Other | 13.9 MB | 05768095101f |
| legacy/pythia410m/ablation_no_l1_seed3/checkpoint-2000/scheduler.pt | Other | 1.7 KB | 3b2455392db2 |
| legacy/pythia410m/ablation_no_l1_seed3/checkpoint-500/expert_pools.pt | Other | 16.7 MB | df5723b22b4c |
| legacy/pythia410m/ablation_no_l1_seed3/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | ae84443ea0d8 |
| legacy/pythia410m/ablation_no_l1_seed3/checkpoint-500/gating_network.pt | Other | 13.9 MB | 909c89304b19 |
| legacy/pythia410m/ablation_no_l1_seed3/checkpoint-500/scheduler.pt | Other | 1.7 KB | 66c01bf5fb42 |
| legacy/pythia410m/ablation_no_layer_emb_seed1/best_model/expert_pools.pt | Other | 16.7 MB | 694bbee24bf8 |
| legacy/pythia410m/ablation_no_layer_emb_seed1/best_model/gated_lora_config.pt | Other | 1.8 KB | 395c5087422e |
| legacy/pythia410m/ablation_no_layer_emb_seed1/best_model/gating_network.pt | Other | 12.7 MB | d366c1b1ec24 |
| legacy/pythia410m/ablation_no_layer_emb_seed1/best_model/scheduler.pt | Other | 1.7 KB | 34bd3772b8c1 |
| legacy/pythia410m/ablation_no_layer_emb_seed1/checkpoint-1000/expert_pools.pt | Other | 16.7 MB | fe42e0b483f4 |
| legacy/pythia410m/ablation_no_layer_emb_seed1/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | 395c5087422e |
| legacy/pythia410m/ablation_no_layer_emb_seed1/checkpoint-1000/gating_network.pt | Other | 12.7 MB | 2eaaa8c4dce9 |
| legacy/pythia410m/ablation_no_layer_emb_seed1/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 0aea463251e0 |
| legacy/pythia410m/ablation_no_layer_emb_seed1/checkpoint-1500/expert_pools.pt | Other | 16.7 MB | c6f7c0d0f828 |
| legacy/pythia410m/ablation_no_layer_emb_seed1/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | 395c5087422e |
| legacy/pythia410m/ablation_no_layer_emb_seed1/checkpoint-1500/gating_network.pt | Other | 12.7 MB | 1bf453014827 |
| legacy/pythia410m/ablation_no_layer_emb_seed1/checkpoint-1500/scheduler.pt | Other | 1.7 KB | ab65e3db4ba5 |
| legacy/pythia410m/ablation_no_layer_emb_seed1/checkpoint-2000/expert_pools.pt | Other | 16.7 MB | a13a26eaa550 |
| legacy/pythia410m/ablation_no_layer_emb_seed1/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | 395c5087422e |
| legacy/pythia410m/ablation_no_layer_emb_seed1/checkpoint-2000/gating_network.pt | Other | 12.7 MB | 405bf6a14bc4 |
| legacy/pythia410m/ablation_no_layer_emb_seed1/checkpoint-2000/scheduler.pt | Other | 1.7 KB | 3b2455392db2 |
| legacy/pythia410m/ablation_no_layer_emb_seed1/checkpoint-500/expert_pools.pt | Other | 16.7 MB | 41d752c8bf69 |
| legacy/pythia410m/ablation_no_layer_emb_seed1/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | 395c5087422e |
| legacy/pythia410m/ablation_no_layer_emb_seed1/checkpoint-500/gating_network.pt | Other | 12.7 MB | 76cd39662613 |
| legacy/pythia410m/ablation_no_layer_emb_seed1/checkpoint-500/scheduler.pt | Other | 1.7 KB | 66c01bf5fb42 |
| legacy/pythia410m/ablation_no_layer_emb_seed2/best_model/expert_pools.pt | Other | 16.7 MB | da05a4d72be6 |
| legacy/pythia410m/ablation_no_layer_emb_seed2/best_model/gated_lora_config.pt | Other | 1.8 KB | 395c5087422e |
| legacy/pythia410m/ablation_no_layer_emb_seed2/best_model/gating_network.pt | Other | 12.7 MB | 680c64a52045 |
| legacy/pythia410m/ablation_no_layer_emb_seed2/best_model/scheduler.pt | Other | 1.7 KB | d5482a786682 |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-1000/expert_pools.pt | Other | 16.7 MB | 40c59e7e8498 |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | 395c5087422e |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-1000/gating_network.pt | Other | 12.7 MB | be5d48801384 |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 0aea463251e0 |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-1500/expert_pools.pt | Other | 16.7 MB | 04faac59e363 |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | 395c5087422e |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-1500/gating_network.pt | Other | 12.7 MB | ed5410e6b4fb |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-1500/scheduler.pt | Other | 1.7 KB | ab65e3db4ba5 |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-2000/expert_pools.pt | Other | 16.7 MB | 175eb3acea44 |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | 395c5087422e |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-2000/gating_network.pt | Other | 12.7 MB | ffa909741102 |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-2000/scheduler.pt | Other | 1.7 KB | 3b2455392db2 |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-2500/expert_pools.pt | Other | 16.7 MB | 91b3e3e37615 |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | 395c5087422e |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-2500/gating_network.pt | Other | 12.7 MB | aa285995311e |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 31bf47791394 |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-3000/expert_pools.pt | Other | 16.7 MB | 87c7dfd4e4aa |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | 395c5087422e |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-3000/gating_network.pt | Other | 12.7 MB | f4ff55ef5a13 |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 502043cb8756 |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-3500/expert_pools.pt | Other | 16.7 MB | de89e0033fc8 |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | 395c5087422e |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-3500/gating_network.pt | Other | 12.7 MB | 03521efb2d13 |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 2be695f86b21 |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-4000/expert_pools.pt | Other | 16.7 MB | 29a24fda2144 |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | 395c5087422e |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-4000/gating_network.pt | Other | 12.7 MB | 4fc22ebba17b |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 673975514d3f |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-500/expert_pools.pt | Other | 16.7 MB | 850dc25612cc |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | 395c5087422e |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-500/gating_network.pt | Other | 12.7 MB | 16d95a938332 |
| legacy/pythia410m/ablation_no_layer_emb_seed2/checkpoint-500/scheduler.pt | Other | 1.7 KB | 66c01bf5fb42 |
| legacy/pythia410m/ablation_no_layer_emb_seed3/best_model/expert_pools.pt | Other | 16.7 MB | dca82915ac40 |
| legacy/pythia410m/ablation_no_layer_emb_seed3/best_model/gated_lora_config.pt | Other | 1.8 KB | 395c5087422e |
| legacy/pythia410m/ablation_no_layer_emb_seed3/best_model/gating_network.pt | Other | 12.7 MB | 229e619918b2 |
| legacy/pythia410m/ablation_no_layer_emb_seed3/best_model/scheduler.pt | Other | 1.7 KB | 6ab07b9b4fa4 |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-1000/expert_pools.pt | Other | 16.7 MB | d7900c32af04 |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | 395c5087422e |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-1000/gating_network.pt | Other | 12.7 MB | 1c154ce27beb |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 0aea463251e0 |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-1500/expert_pools.pt | Other | 16.7 MB | 8038c9dce013 |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | 395c5087422e |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-1500/gating_network.pt | Other | 12.7 MB | ab5318a70451 |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-1500/scheduler.pt | Other | 1.7 KB | ab65e3db4ba5 |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-2000/expert_pools.pt | Other | 16.7 MB | ade9363006e3 |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | 395c5087422e |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-2000/gating_network.pt | Other | 12.7 MB | 5f3a1a701ea6 |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-2000/scheduler.pt | Other | 1.7 KB | 3b2455392db2 |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-2500/expert_pools.pt | Other | 16.7 MB | 877da46fadee |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | 395c5087422e |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-2500/gating_network.pt | Other | 12.7 MB | 0ab45a789af3 |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 31bf47791394 |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-3000/expert_pools.pt | Other | 16.7 MB | 87a8311350d3 |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | 395c5087422e |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-3000/gating_network.pt | Other | 12.7 MB | 647fce0c6cd7 |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 502043cb8756 |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-3500/expert_pools.pt | Other | 16.7 MB | e3e744d76290 |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | 395c5087422e |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-3500/gating_network.pt | Other | 12.7 MB | de16d6e4bdb0 |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 2be695f86b21 |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-4000/expert_pools.pt | Other | 16.7 MB | a79d8a7410df |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | 395c5087422e |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-4000/gating_network.pt | Other | 12.7 MB | 88ee34a0ac2b |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 673975514d3f |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-500/expert_pools.pt | Other | 16.7 MB | 3e0638382110 |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | 395c5087422e |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-500/gating_network.pt | Other | 12.7 MB | 8ea671cd1f25 |
| legacy/pythia410m/ablation_no_layer_emb_seed3/checkpoint-500/scheduler.pt | Other | 1.7 KB | 66c01bf5fb42 |
| legacy/pythia410m/ablation_partial_gating_seed1/best_model/expert_pools.pt | Other | 16.7 MB | 0e154055076d |
| legacy/pythia410m/ablation_partial_gating_seed1/best_model/gated_lora_config.pt | Other | 1.8 KB | d936a70c58c4 |
| legacy/pythia410m/ablation_partial_gating_seed1/best_model/gating_network.pt | Other | 13.9 MB | 98ceb718ccb6 |
| legacy/pythia410m/ablation_partial_gating_seed1/best_model/scheduler.pt | Other | 1.7 KB | db9980d2176e |
| legacy/pythia410m/ablation_partial_gating_seed1/checkpoint-1000/expert_pools.pt | Other | 16.7 MB | adb2bb98360e |
| legacy/pythia410m/ablation_partial_gating_seed1/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | d936a70c58c4 |
| legacy/pythia410m/ablation_partial_gating_seed1/checkpoint-1000/gating_network.pt | Other | 13.9 MB | b99a3ed46db2 |
| legacy/pythia410m/ablation_partial_gating_seed1/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 0aea463251e0 |
| legacy/pythia410m/ablation_partial_gating_seed1/checkpoint-1500/expert_pools.pt | Other | 16.7 MB | b5cf3f3e14c7 |
| legacy/pythia410m/ablation_partial_gating_seed1/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | d936a70c58c4 |
| legacy/pythia410m/ablation_partial_gating_seed1/checkpoint-1500/gating_network.pt | Other | 13.9 MB | f56472cab3d8 |
| legacy/pythia410m/ablation_partial_gating_seed1/checkpoint-1500/scheduler.pt | Other | 1.7 KB | ab65e3db4ba5 |
| legacy/pythia410m/ablation_partial_gating_seed1/checkpoint-2000/expert_pools.pt | Other | 16.7 MB | de848b2e50d8 |
| legacy/pythia410m/ablation_partial_gating_seed1/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | d936a70c58c4 |
| legacy/pythia410m/ablation_partial_gating_seed1/checkpoint-2000/gating_network.pt | Other | 13.9 MB | 2bc02340c9ba |
| legacy/pythia410m/ablation_partial_gating_seed1/checkpoint-2000/scheduler.pt | Other | 1.7 KB | 3b2455392db2 |
| legacy/pythia410m/ablation_partial_gating_seed1/checkpoint-500/expert_pools.pt | Other | 16.7 MB | 62e228ed5e03 |
| legacy/pythia410m/ablation_partial_gating_seed1/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | d936a70c58c4 |
| legacy/pythia410m/ablation_partial_gating_seed1/checkpoint-500/gating_network.pt | Other | 13.9 MB | 59b4e8552847 |
| legacy/pythia410m/ablation_partial_gating_seed1/checkpoint-500/scheduler.pt | Other | 1.7 KB | 66c01bf5fb42 |
| legacy/pythia410m/ablation_partial_gating_seed2/best_model/expert_pools.pt | Other | 16.7 MB | 5c31ad14fb3f |
| legacy/pythia410m/ablation_partial_gating_seed2/best_model/gated_lora_config.pt | Other | 1.8 KB | d936a70c58c4 |
| legacy/pythia410m/ablation_partial_gating_seed2/best_model/gating_network.pt | Other | 13.9 MB | 51cac332f884 |
| legacy/pythia410m/ablation_partial_gating_seed2/best_model/scheduler.pt | Other | 1.7 KB | bf912dda7335 |
| legacy/pythia410m/ablation_partial_gating_seed2/checkpoint-1000/expert_pools.pt | Other | 16.7 MB | 0ac9aaa4ca9f |
| legacy/pythia410m/ablation_partial_gating_seed2/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | d936a70c58c4 |
| legacy/pythia410m/ablation_partial_gating_seed2/checkpoint-1000/gating_network.pt | Other | 13.9 MB | 1d01f25b2b8c |
| legacy/pythia410m/ablation_partial_gating_seed2/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 0aea463251e0 |
| legacy/pythia410m/ablation_partial_gating_seed2/checkpoint-1500/expert_pools.pt | Other | 16.7 MB | 56caad3d58ac |
| legacy/pythia410m/ablation_partial_gating_seed2/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | d936a70c58c4 |
| legacy/pythia410m/ablation_partial_gating_seed2/checkpoint-1500/gating_network.pt | Other | 13.9 MB | ed0a60e8b7cf |
| legacy/pythia410m/ablation_partial_gating_seed2/checkpoint-1500/scheduler.pt | Other | 1.7 KB | ab65e3db4ba5 |
| legacy/pythia410m/ablation_partial_gating_seed2/checkpoint-2000/expert_pools.pt | Other | 16.7 MB | 3a07a090e39f |
| legacy/pythia410m/ablation_partial_gating_seed2/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | d936a70c58c4 |
| legacy/pythia410m/ablation_partial_gating_seed2/checkpoint-2000/gating_network.pt | Other | 13.9 MB | e54b7764845a |
| legacy/pythia410m/ablation_partial_gating_seed2/checkpoint-2000/scheduler.pt | Other | 1.7 KB | 3b2455392db2 |
| legacy/pythia410m/ablation_partial_gating_seed2/checkpoint-500/expert_pools.pt | Other | 16.7 MB | e1e38b746448 |
| legacy/pythia410m/ablation_partial_gating_seed2/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | d936a70c58c4 |
| legacy/pythia410m/ablation_partial_gating_seed2/checkpoint-500/gating_network.pt | Other | 13.9 MB | 934cfdb5ce16 |
| legacy/pythia410m/ablation_partial_gating_seed2/checkpoint-500/scheduler.pt | Other | 1.7 KB | 66c01bf5fb42 |
| legacy/pythia410m/ablation_partial_gating_seed3/best_model/expert_pools.pt | Other | 16.7 MB | 3ef3d9a0f872 |
| legacy/pythia410m/ablation_partial_gating_seed3/best_model/gated_lora_config.pt | Other | 1.8 KB | d936a70c58c4 |
| legacy/pythia410m/ablation_partial_gating_seed3/best_model/gating_network.pt | Other | 13.9 MB | a7a84d22e21c |
| legacy/pythia410m/ablation_partial_gating_seed3/best_model/scheduler.pt | Other | 1.7 KB | bf912dda7335 |
| legacy/pythia410m/ablation_partial_gating_seed3/checkpoint-1000/expert_pools.pt | Other | 16.7 MB | c643ff455ea8 |
| legacy/pythia410m/ablation_partial_gating_seed3/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | d936a70c58c4 |
| legacy/pythia410m/ablation_partial_gating_seed3/checkpoint-1000/gating_network.pt | Other | 13.9 MB | 5ca91288c8ef |
| legacy/pythia410m/ablation_partial_gating_seed3/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 0aea463251e0 |
| legacy/pythia410m/ablation_partial_gating_seed3/checkpoint-1500/expert_pools.pt | Other | 16.7 MB | 90d64cf8d4ae |
| legacy/pythia410m/ablation_partial_gating_seed3/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | d936a70c58c4 |
| legacy/pythia410m/ablation_partial_gating_seed3/checkpoint-1500/gating_network.pt | Other | 13.9 MB | 9fa5d737a3de |
| legacy/pythia410m/ablation_partial_gating_seed3/checkpoint-1500/scheduler.pt | Other | 1.7 KB | ab65e3db4ba5 |
| legacy/pythia410m/ablation_partial_gating_seed3/checkpoint-2000/expert_pools.pt | Other | 16.7 MB | e38b7173c0ba |
| legacy/pythia410m/ablation_partial_gating_seed3/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | d936a70c58c4 |
| legacy/pythia410m/ablation_partial_gating_seed3/checkpoint-2000/gating_network.pt | Other | 13.9 MB | 1f5427f3fa53 |
| legacy/pythia410m/ablation_partial_gating_seed3/checkpoint-2000/scheduler.pt | Other | 1.7 KB | 3b2455392db2 |
| legacy/pythia410m/ablation_partial_gating_seed3/checkpoint-500/expert_pools.pt | Other | 16.7 MB | 2d26d427d53e |
| legacy/pythia410m/ablation_partial_gating_seed3/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | d936a70c58c4 |
| legacy/pythia410m/ablation_partial_gating_seed3/checkpoint-500/gating_network.pt | Other | 13.9 MB | 18e376836f38 |
| legacy/pythia410m/ablation_partial_gating_seed3/checkpoint-500/scheduler.pt | Other | 1.7 KB | 66c01bf5fb42 |
| legacy/pythia410m/exp2_gated_2experts_seed1/best_model/expert_pools.pt | Other | 7.2 MB | 590ae5784fdd |
| legacy/pythia410m/exp2_gated_2experts_seed1/best_model/gated_lora_config.pt | Other | 1.8 KB | d3f393b0f70b |
| legacy/pythia410m/exp2_gated_2experts_seed1/best_model/gating_network.pt | Other | 13.8 MB | 2edb8e1457ba |
| legacy/pythia410m/exp2_gated_2experts_seed1/best_model/scheduler.pt | Other | 1.7 KB | 0a420609c446 |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-1000/expert_pools.pt | Other | 7.2 MB | 30a3ab8e6cb6 |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | d3f393b0f70b |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-1000/gating_network.pt | Other | 13.8 MB | bfed975e48e5 |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 0aea463251e0 |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-1500/expert_pools.pt | Other | 7.2 MB | 078b33d20cc7 |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | d3f393b0f70b |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-1500/gating_network.pt | Other | 13.8 MB | ed5200ecd414 |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-1500/scheduler.pt | Other | 1.7 KB | ab65e3db4ba5 |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-2000/expert_pools.pt | Other | 7.2 MB | 3cbced1b98a2 |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | d3f393b0f70b |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-2000/gating_network.pt | Other | 13.8 MB | feb67888ed48 |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-2000/scheduler.pt | Other | 1.7 KB | 3b2455392db2 |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-2500/expert_pools.pt | Other | 7.2 MB | 4c90c13515c4 |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | d3f393b0f70b |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-2500/gating_network.pt | Other | 13.8 MB | 37242630512e |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 31bf47791394 |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-3000/expert_pools.pt | Other | 7.2 MB | 27c7682b08e1 |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | d3f393b0f70b |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-3000/gating_network.pt | Other | 13.8 MB | ec25787b49a6 |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 502043cb8756 |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-3500/expert_pools.pt | Other | 7.2 MB | 01aab98de7fc |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | d3f393b0f70b |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-3500/gating_network.pt | Other | 13.8 MB | 3970812f9215 |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 2be695f86b21 |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-4000/expert_pools.pt | Other | 7.2 MB | 12e975217612 |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | d3f393b0f70b |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-4000/gating_network.pt | Other | 13.8 MB | 2dc9f71fc87c |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 673975514d3f |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-500/expert_pools.pt | Other | 7.2 MB | 6e80a7859513 |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | d3f393b0f70b |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-500/gating_network.pt | Other | 13.8 MB | 9e3d677d8825 |
| legacy/pythia410m/exp2_gated_2experts_seed1/checkpoint-500/scheduler.pt | Other | 1.7 KB | 66c01bf5fb42 |
| legacy/pythia410m/exp2_gated_2experts_seed1/final_model/expert_pools.pt | Other | 7.2 MB | 7f773378af0e |
| legacy/pythia410m/exp2_gated_2experts_seed1/final_model/gated_lora_config.pt | Other | 1.8 KB | d3f393b0f70b |
| legacy/pythia410m/exp2_gated_2experts_seed1/final_model/gating_network.pt | Other | 13.8 MB | 6bb2c3a20b7a |
| legacy/pythia410m/exp2_gated_2experts_seed1/final_model/scheduler.pt | Other | 1.7 KB | 4b13ed54111b |
| legacy/pythia410m/exp2_gated_2experts_seed1/visualizations/exp2_gated_2experts_seed1_entropy_per_layer.png | Other | 43.1 KB | 6b9c19c1c676 |
| legacy/pythia410m/exp2_gated_2experts_seed1/visualizations/exp2_gated_2experts_seed1_layer_expert_heatmap.png | Other | 100.8 KB | 9a665160d085 |
| legacy/pythia410m/exp2_gated_2experts_seed1/visualizations/exp2_gated_2experts_seed1_task_expert_usage.png | Other | 38.5 KB | 0897104e3dca |
| legacy/pythia410m/exp2_gated_2experts_seed1/visualizations/exp2_gated_2experts_seed1_token_routing_1.png | Other | 89.6 KB | 0dcf64107cd5 |
| legacy/pythia410m/exp2_gated_2experts_seed1/visualizations/exp2_gated_2experts_seed1_token_routing_2.png | Other | 89.4 KB | d5aa02d9140d |
| legacy/pythia410m/exp2_gated_2experts_seed1/visualizations/exp2_gated_2experts_seed1_token_routing_3.png | Other | 89.8 KB | a2007350a98e |
| legacy/pythia410m/exp2_gated_2experts_seed2/best_model/expert_pools.pt | Other | 7.2 MB | ed5a51637ad4 |
| legacy/pythia410m/exp2_gated_2experts_seed2/best_model/gated_lora_config.pt | Other | 1.8 KB | d3f393b0f70b |
| legacy/pythia410m/exp2_gated_2experts_seed2/best_model/gating_network.pt | Other | 13.8 MB | 3c2c80309d05 |
| legacy/pythia410m/exp2_gated_2experts_seed2/best_model/scheduler.pt | Other | 1.7 KB | b51dfc15ac23 |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-1000/expert_pools.pt | Other | 7.2 MB | 55b4e2994634 |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | d3f393b0f70b |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-1000/gating_network.pt | Other | 13.8 MB | d0ee2669c9b7 |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 0aea463251e0 |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-1500/expert_pools.pt | Other | 7.2 MB | be6b56d9c125 |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | d3f393b0f70b |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-1500/gating_network.pt | Other | 13.8 MB | 0969776c7c35 |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-1500/scheduler.pt | Other | 1.7 KB | ab65e3db4ba5 |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-2000/expert_pools.pt | Other | 7.2 MB | 969cd13faf42 |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | d3f393b0f70b |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-2000/gating_network.pt | Other | 13.8 MB | 6cfe40d4c5cb |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-2000/scheduler.pt | Other | 1.7 KB | 3b2455392db2 |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-2500/expert_pools.pt | Other | 7.2 MB | 912e36501f16 |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | d3f393b0f70b |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-2500/gating_network.pt | Other | 13.8 MB | 4545dae794f9 |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 31bf47791394 |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-3000/expert_pools.pt | Other | 7.2 MB | 8d814f9c189a |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | d3f393b0f70b |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-3000/gating_network.pt | Other | 13.8 MB | c25fac784337 |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 502043cb8756 |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-3500/expert_pools.pt | Other | 7.2 MB | 35a41d12ae7e |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | d3f393b0f70b |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-3500/gating_network.pt | Other | 13.8 MB | dfe0c10ae83f |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 2be695f86b21 |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-4000/expert_pools.pt | Other | 7.2 MB | aacf178073d1 |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | d3f393b0f70b |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-4000/gating_network.pt | Other | 13.8 MB | 4f1e728a204d |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 673975514d3f |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-500/expert_pools.pt | Other | 7.2 MB | f1181abc00cc |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | d3f393b0f70b |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-500/gating_network.pt | Other | 13.8 MB | 089a3b5b6800 |
| legacy/pythia410m/exp2_gated_2experts_seed2/checkpoint-500/scheduler.pt | Other | 1.7 KB | 66c01bf5fb42 |
| legacy/pythia410m/exp2_gated_2experts_seed2/final_model/expert_pools.pt | Other | 7.2 MB | 0af6c69b949b |
| legacy/pythia410m/exp2_gated_2experts_seed2/final_model/gated_lora_config.pt | Other | 1.8 KB | d3f393b0f70b |
| legacy/pythia410m/exp2_gated_2experts_seed2/final_model/gating_network.pt | Other | 13.8 MB | 4183133b2bb0 |
| legacy/pythia410m/exp2_gated_2experts_seed2/final_model/scheduler.pt | Other | 1.7 KB | 4b13ed54111b |
| legacy/pythia410m/exp2_gated_2experts_seed2/visualizations/exp2_gated_2experts_seed2_entropy_per_layer.png | Other | 42.7 KB | 730498ef580d |
| legacy/pythia410m/exp2_gated_2experts_seed2/visualizations/exp2_gated_2experts_seed2_layer_expert_heatmap.png | Other | 101.6 KB | e6a1bb1f9d8e |
| legacy/pythia410m/exp2_gated_2experts_seed2/visualizations/exp2_gated_2experts_seed2_task_expert_usage.png | Other | 38.1 KB | 797ee5900f1f |
| legacy/pythia410m/exp2_gated_2experts_seed2/visualizations/exp2_gated_2experts_seed2_token_routing_1.png | Other | 89.4 KB | 11b9e2bbd661 |
| legacy/pythia410m/exp2_gated_2experts_seed2/visualizations/exp2_gated_2experts_seed2_token_routing_2.png | Other | 89.5 KB | 7c3581f79911 |
| legacy/pythia410m/exp2_gated_2experts_seed2/visualizations/exp2_gated_2experts_seed2_token_routing_3.png | Other | 89.8 KB | 50aa85d21cba |
| legacy/pythia410m/exp2_gated_2experts_seed3/best_model/expert_pools.pt | Other | 7.2 MB | c2e95299fc09 |
| legacy/pythia410m/exp2_gated_2experts_seed3/best_model/gated_lora_config.pt | Other | 1.8 KB | d3f393b0f70b |
| legacy/pythia410m/exp2_gated_2experts_seed3/best_model/gating_network.pt | Other | 13.8 MB | 47d40728146e |
| legacy/pythia410m/exp2_gated_2experts_seed3/best_model/scheduler.pt | Other | 1.7 KB | b51dfc15ac23 |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-1000/expert_pools.pt | Other | 7.2 MB | 321cb5f68699 |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | d3f393b0f70b |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-1000/gating_network.pt | Other | 13.8 MB | 6017a9603f2c |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 0aea463251e0 |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-1500/expert_pools.pt | Other | 7.2 MB | a6db2e89170a |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | d3f393b0f70b |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-1500/gating_network.pt | Other | 13.8 MB | 4ca00b5db13c |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-1500/scheduler.pt | Other | 1.7 KB | ab65e3db4ba5 |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-2000/expert_pools.pt | Other | 7.2 MB | fb49601dfa34 |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | d3f393b0f70b |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-2000/gating_network.pt | Other | 13.8 MB | 66d49e84d7bd |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-2000/scheduler.pt | Other | 1.7 KB | 3b2455392db2 |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-2500/expert_pools.pt | Other | 7.2 MB | 13af760a361e |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | d3f393b0f70b |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-2500/gating_network.pt | Other | 13.8 MB | 13ca6585644f |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 31bf47791394 |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-3000/expert_pools.pt | Other | 7.2 MB | 637e29684adb |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | d3f393b0f70b |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-3000/gating_network.pt | Other | 13.8 MB | bfe72fac2475 |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 502043cb8756 |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-3500/expert_pools.pt | Other | 7.2 MB | 2b72ca34818a |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | d3f393b0f70b |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-3500/gating_network.pt | Other | 13.8 MB | 60a663955c12 |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 2be695f86b21 |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-4000/expert_pools.pt | Other | 7.2 MB | eb8f17d920a6 |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | d3f393b0f70b |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-4000/gating_network.pt | Other | 13.8 MB | 164fbd72e34c |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 673975514d3f |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-500/expert_pools.pt | Other | 7.2 MB | e73a5fddb8e7 |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | d3f393b0f70b |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-500/gating_network.pt | Other | 13.8 MB | 9e74d5792704 |
| legacy/pythia410m/exp2_gated_2experts_seed3/checkpoint-500/scheduler.pt | Other | 1.7 KB | 66c01bf5fb42 |
| legacy/pythia410m/exp2_gated_2experts_seed3/final_model/expert_pools.pt | Other | 7.2 MB | 87fabfd6fc0e |
| legacy/pythia410m/exp2_gated_2experts_seed3/final_model/gated_lora_config.pt | Other | 1.8 KB | d3f393b0f70b |
| legacy/pythia410m/exp2_gated_2experts_seed3/final_model/gating_network.pt | Other | 13.8 MB | 49f620d47633 |
| legacy/pythia410m/exp2_gated_2experts_seed3/final_model/scheduler.pt | Other | 1.7 KB | 4b13ed54111b |
| legacy/pythia410m/exp2_gated_2experts_seed3/visualizations/exp2_gated_2experts_seed3_entropy_per_layer.png | Other | 43.4 KB | c779251e8f66 |
| legacy/pythia410m/exp2_gated_2experts_seed3/visualizations/exp2_gated_2experts_seed3_layer_expert_heatmap.png | Other | 98.6 KB | fa7d33f62f36 |
| legacy/pythia410m/exp2_gated_2experts_seed3/visualizations/exp2_gated_2experts_seed3_task_expert_usage.png | Other | 38.7 KB | dfd1380e91e1 |
| legacy/pythia410m/exp2_gated_2experts_seed3/visualizations/exp2_gated_2experts_seed3_token_routing_1.png | Other | 89.9 KB | 120c2493d10e |
| legacy/pythia410m/exp2_gated_2experts_seed3/visualizations/exp2_gated_2experts_seed3_token_routing_2.png | Other | 89.7 KB | 5cd6d99d2c2c |
| legacy/pythia410m/exp2_gated_2experts_seed3/visualizations/exp2_gated_2experts_seed3_token_routing_3.png | Other | 90.0 KB | b45f99f0bf7a |
| legacy/pythia410m/exp3_gated_3experts_seed1/best_model/expert_pools.pt | Other | 16.7 MB | 7da47ab32c4b |
| legacy/pythia410m/exp3_gated_3experts_seed1/best_model/gated_lora_config.pt | Other | 1.8 KB | 10f76a249838 |
| legacy/pythia410m/exp3_gated_3experts_seed1/best_model/gating_network.pt | Other | 13.9 MB | 01a85f99e50f |
| legacy/pythia410m/exp3_gated_3experts_seed1/best_model/scheduler.pt | Other | 1.7 KB | b2e0d0974bd3 |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-1000/expert_pools.pt | Other | 16.7 MB | fa38fab5259f |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | 10f76a249838 |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-1000/gating_network.pt | Other | 13.9 MB | 396a2451a3e2 |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 0aea463251e0 |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-1500/expert_pools.pt | Other | 16.7 MB | 4bd4dedc2d77 |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | 10f76a249838 |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-1500/gating_network.pt | Other | 13.9 MB | c3b14daa5e73 |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-1500/scheduler.pt | Other | 1.7 KB | ab65e3db4ba5 |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-2000/expert_pools.pt | Other | 16.7 MB | d927a7ebc763 |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | 10f76a249838 |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-2000/gating_network.pt | Other | 13.9 MB | 7516ca544f39 |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-2000/scheduler.pt | Other | 1.7 KB | 3b2455392db2 |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-2500/expert_pools.pt | Other | 16.7 MB | d5f32f3acb60 |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | 10f76a249838 |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-2500/gating_network.pt | Other | 13.9 MB | 51eea3ce46a3 |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 31bf47791394 |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-3000/expert_pools.pt | Other | 16.7 MB | 514821240383 |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | 10f76a249838 |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-3000/gating_network.pt | Other | 13.9 MB | a01a7446f122 |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 502043cb8756 |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-3500/expert_pools.pt | Other | 16.7 MB | 4cc5d0d5daa3 |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | 10f76a249838 |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-3500/gating_network.pt | Other | 13.9 MB | 638bf104ee22 |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 2be695f86b21 |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-4000/expert_pools.pt | Other | 16.7 MB | d7eec099670d |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | 10f76a249838 |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-4000/gating_network.pt | Other | 13.9 MB | 339f80d7dfc1 |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 673975514d3f |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-500/expert_pools.pt | Other | 16.7 MB | 332c24cbeee5 |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | 10f76a249838 |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-500/gating_network.pt | Other | 13.9 MB | 36e49ad6defb |
| legacy/pythia410m/exp3_gated_3experts_seed1/checkpoint-500/scheduler.pt | Other | 1.7 KB | 66c01bf5fb42 |
| legacy/pythia410m/exp3_gated_3experts_seed1/final_model/expert_pools.pt | Other | 16.7 MB | 7ef25eeb46f5 |
| legacy/pythia410m/exp3_gated_3experts_seed1/final_model/gated_lora_config.pt | Other | 1.8 KB | 10f76a249838 |
| legacy/pythia410m/exp3_gated_3experts_seed1/final_model/gating_network.pt | Other | 13.9 MB | b79a326f7207 |
| legacy/pythia410m/exp3_gated_3experts_seed1/final_model/scheduler.pt | Other | 1.7 KB | 4b13ed54111b |
| legacy/pythia410m/exp3_gated_3experts_seed1/visualizations/exp3_gated_3experts_seed1_entropy_per_layer.png | Other | 42.4 KB | 9fcaacd542be |
| legacy/pythia410m/exp3_gated_3experts_seed1/visualizations/exp3_gated_3experts_seed1_layer_expert_heatmap.png | Other | 102.2 KB | bed172d64f3c |
| legacy/pythia410m/exp3_gated_3experts_seed1/visualizations/exp3_gated_3experts_seed1_task_expert_usage.png | Other | 38.1 KB | bca526b927d1 |
| legacy/pythia410m/exp3_gated_3experts_seed1/visualizations/exp3_gated_3experts_seed1_token_routing_1.png | Other | 91.7 KB | 66818850396f |
| legacy/pythia410m/exp3_gated_3experts_seed1/visualizations/exp3_gated_3experts_seed1_token_routing_2.png | Other | 91.9 KB | de4d8eea262d |
| legacy/pythia410m/exp3_gated_3experts_seed1/visualizations/exp3_gated_3experts_seed1_token_routing_3.png | Other | 92.0 KB | 37371f81f229 |
| legacy/pythia410m/exp3_gated_3experts_seed2/best_model/expert_pools.pt | Other | 16.7 MB | 8d0db06522ca |
| legacy/pythia410m/exp3_gated_3experts_seed2/best_model/gated_lora_config.pt | Other | 1.8 KB | 10f76a249838 |
| legacy/pythia410m/exp3_gated_3experts_seed2/best_model/gating_network.pt | Other | 13.9 MB | 57d899319d79 |
| legacy/pythia410m/exp3_gated_3experts_seed2/best_model/scheduler.pt | Other | 1.7 KB | d5482a786682 |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-1000/expert_pools.pt | Other | 16.7 MB | fc201ffbdf0a |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | 10f76a249838 |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-1000/gating_network.pt | Other | 13.9 MB | ced287d5e980 |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 0aea463251e0 |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-1500/expert_pools.pt | Other | 16.7 MB | c5e0898a806d |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | 10f76a249838 |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-1500/gating_network.pt | Other | 13.9 MB | a11de3c1bd90 |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-1500/scheduler.pt | Other | 1.7 KB | ab65e3db4ba5 |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-2000/expert_pools.pt | Other | 16.7 MB | 4d9e013392f1 |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | 10f76a249838 |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-2000/gating_network.pt | Other | 13.9 MB | 900b08cb6bf0 |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-2000/scheduler.pt | Other | 1.7 KB | 3b2455392db2 |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-2500/expert_pools.pt | Other | 16.7 MB | 6c64a038d7ec |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | 10f76a249838 |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-2500/gating_network.pt | Other | 13.9 MB | 894c6404861e |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 31bf47791394 |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-3000/expert_pools.pt | Other | 16.7 MB | 67856dc4b510 |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | 10f76a249838 |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-3000/gating_network.pt | Other | 13.9 MB | 6bbda91adabe |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 502043cb8756 |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-3500/expert_pools.pt | Other | 16.7 MB | dbd6948faa9b |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | 10f76a249838 |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-3500/gating_network.pt | Other | 13.9 MB | dc105f725629 |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 2be695f86b21 |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-4000/expert_pools.pt | Other | 16.7 MB | 46d55ae270af |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | 10f76a249838 |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-4000/gating_network.pt | Other | 13.9 MB | 4510982de385 |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 673975514d3f |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-500/expert_pools.pt | Other | 16.7 MB | e9a6a9fb6898 |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | 10f76a249838 |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-500/gating_network.pt | Other | 13.9 MB | 982319ecf826 |
| legacy/pythia410m/exp3_gated_3experts_seed2/checkpoint-500/scheduler.pt | Other | 1.7 KB | 66c01bf5fb42 |
| legacy/pythia410m/exp3_gated_3experts_seed2/final_model/expert_pools.pt | Other | 16.7 MB | fe8be931926c |
| legacy/pythia410m/exp3_gated_3experts_seed2/final_model/gated_lora_config.pt | Other | 1.8 KB | 10f76a249838 |
| legacy/pythia410m/exp3_gated_3experts_seed2/final_model/gating_network.pt | Other | 13.9 MB | 9b1f03c07c1f |
| legacy/pythia410m/exp3_gated_3experts_seed2/final_model/scheduler.pt | Other | 1.7 KB | 4b13ed54111b |
| legacy/pythia410m/exp3_gated_3experts_seed2/visualizations/exp3_gated_3experts_seed2_entropy_per_layer.png | Other | 42.7 KB | cf2b28cfdf48 |
| legacy/pythia410m/exp3_gated_3experts_seed2/visualizations/exp3_gated_3experts_seed2_layer_expert_heatmap.png | Other | 99.6 KB | f23cc61e65c8 |
| legacy/pythia410m/exp3_gated_3experts_seed2/visualizations/exp3_gated_3experts_seed2_task_expert_usage.png | Other | 39.2 KB | 5a2fd5022bd8 |
| legacy/pythia410m/exp3_gated_3experts_seed2/visualizations/exp3_gated_3experts_seed2_token_routing_1.png | Other | 91.1 KB | 89f23b5e8c2b |
| legacy/pythia410m/exp3_gated_3experts_seed2/visualizations/exp3_gated_3experts_seed2_token_routing_2.png | Other | 91.3 KB | 68101f454d8b |
| legacy/pythia410m/exp3_gated_3experts_seed2/visualizations/exp3_gated_3experts_seed2_token_routing_3.png | Other | 91.1 KB | 67939ac2d9e7 |
| legacy/pythia410m/exp3_gated_3experts_seed3/best_model/expert_pools.pt | Other | 16.7 MB | 81de4419a01e |
| legacy/pythia410m/exp3_gated_3experts_seed3/best_model/gated_lora_config.pt | Other | 1.8 KB | 10f76a249838 |
| legacy/pythia410m/exp3_gated_3experts_seed3/best_model/gating_network.pt | Other | 13.9 MB | 8ddc2d2e1daa |
| legacy/pythia410m/exp3_gated_3experts_seed3/best_model/scheduler.pt | Other | 1.7 KB | 34bd3772b8c1 |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-1000/expert_pools.pt | Other | 16.7 MB | 35fb0eaf2b48 |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | 10f76a249838 |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-1000/gating_network.pt | Other | 13.9 MB | 905f57585068 |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 0aea463251e0 |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-1500/expert_pools.pt | Other | 16.7 MB | aa463ac8c245 |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | 10f76a249838 |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-1500/gating_network.pt | Other | 13.9 MB | 2c18956f5bad |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-1500/scheduler.pt | Other | 1.7 KB | ab65e3db4ba5 |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-2000/expert_pools.pt | Other | 16.7 MB | c17beaff9862 |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | 10f76a249838 |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-2000/gating_network.pt | Other | 13.9 MB | 2092e080657b |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-2000/scheduler.pt | Other | 1.7 KB | 3b2455392db2 |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-2500/expert_pools.pt | Other | 16.7 MB | 90ea2b95b261 |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | 10f76a249838 |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-2500/gating_network.pt | Other | 13.9 MB | 5f79030d1fa1 |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 31bf47791394 |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-3000/expert_pools.pt | Other | 16.7 MB | aaec41b13056 |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | 10f76a249838 |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-3000/gating_network.pt | Other | 13.9 MB | cdd839f3bc2e |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 502043cb8756 |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-3500/expert_pools.pt | Other | 16.7 MB | 811bb4172275 |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | 10f76a249838 |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-3500/gating_network.pt | Other | 13.9 MB | 1a1be92dfec6 |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 2be695f86b21 |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-4000/expert_pools.pt | Other | 16.7 MB | 079d3955dd39 |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | 10f76a249838 |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-4000/gating_network.pt | Other | 13.9 MB | 7b40630226d0 |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 673975514d3f |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-500/expert_pools.pt | Other | 16.7 MB | 36ea561a9b02 |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | 10f76a249838 |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-500/gating_network.pt | Other | 13.9 MB | 375c5f49b81b |
| legacy/pythia410m/exp3_gated_3experts_seed3/checkpoint-500/scheduler.pt | Other | 1.7 KB | 66c01bf5fb42 |
| legacy/pythia410m/exp3_gated_3experts_seed3/final_model/expert_pools.pt | Other | 16.7 MB | f72948f4bcf3 |
| legacy/pythia410m/exp3_gated_3experts_seed3/final_model/gated_lora_config.pt | Other | 1.8 KB | 10f76a249838 |
| legacy/pythia410m/exp3_gated_3experts_seed3/final_model/gating_network.pt | Other | 13.9 MB | ec8ad9165fa0 |
| legacy/pythia410m/exp3_gated_3experts_seed3/final_model/scheduler.pt | Other | 1.7 KB | 4b13ed54111b |
| legacy/pythia410m/exp3_gated_3experts_seed3/visualizations/exp3_gated_3experts_seed3_entropy_per_layer.png | Other | 42.8 KB | deae83415ed6 |
| legacy/pythia410m/exp3_gated_3experts_seed3/visualizations/exp3_gated_3experts_seed3_layer_expert_heatmap.png | Other | 99.6 KB | 81cb933ce69c |
| legacy/pythia410m/exp3_gated_3experts_seed3/visualizations/exp3_gated_3experts_seed3_task_expert_usage.png | Other | 38.4 KB | f16d4167e8e7 |
| legacy/pythia410m/exp3_gated_3experts_seed3/visualizations/exp3_gated_3experts_seed3_token_routing_1.png | Other | 91.5 KB | b099bee41dd7 |
| legacy/pythia410m/exp3_gated_3experts_seed3/visualizations/exp3_gated_3experts_seed3_token_routing_2.png | Other | 91.8 KB | 66da3e741b79 |
| legacy/pythia410m/exp3_gated_3experts_seed3/visualizations/exp3_gated_3experts_seed3_token_routing_3.png | Other | 91.8 KB | 99388987d15f |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/best_model/expert_pools.pt | Other | 16.7 MB | b8442ef97eeb |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/best_model/gated_lora_config.pt | Other | 1.8 KB | ef9b75d6d4e4 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/best_model/gating_network.pt | Other | 13.9 MB | 4d60f3e15dd1 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/best_model/scheduler.pt | Other | 1.7 KB | b2e0d0974bd3 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-1000/expert_pools.pt | Other | 16.7 MB | c191bf65a814 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | ef9b75d6d4e4 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-1000/gating_network.pt | Other | 13.9 MB | 0715e4715738 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 0aea463251e0 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-1500/expert_pools.pt | Other | 16.7 MB | f6eac1eb5132 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | ef9b75d6d4e4 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-1500/gating_network.pt | Other | 13.9 MB | c45f20d6e176 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-1500/scheduler.pt | Other | 1.7 KB | ab65e3db4ba5 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-2000/expert_pools.pt | Other | 16.7 MB | 50b7fa8be280 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | ef9b75d6d4e4 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-2000/gating_network.pt | Other | 13.9 MB | a9a67ebe0ade |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-2000/scheduler.pt | Other | 1.7 KB | 3b2455392db2 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-2500/expert_pools.pt | Other | 16.7 MB | 1b44d7a13f25 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | ef9b75d6d4e4 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-2500/gating_network.pt | Other | 13.9 MB | b6d6439c70fe |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 31bf47791394 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-3000/expert_pools.pt | Other | 16.7 MB | 409b4ef74186 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | ef9b75d6d4e4 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-3000/gating_network.pt | Other | 13.9 MB | 135b329fcba3 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 502043cb8756 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-3500/expert_pools.pt | Other | 16.7 MB | 39943ddfb42e |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | ef9b75d6d4e4 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-3500/gating_network.pt | Other | 13.9 MB | eda654b5e2e2 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 2be695f86b21 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-4000/expert_pools.pt | Other | 16.7 MB | b36c89d1d11f |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | ef9b75d6d4e4 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-4000/gating_network.pt | Other | 13.9 MB | 3ea67b25a123 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 673975514d3f |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-500/expert_pools.pt | Other | 16.7 MB | a6f5c0a366dc |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | ef9b75d6d4e4 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-500/gating_network.pt | Other | 13.9 MB | 740ccef4f0eb |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/checkpoint-500/scheduler.pt | Other | 1.7 KB | 66c01bf5fb42 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/final_model/expert_pools.pt | Other | 16.7 MB | 595ce4ad2588 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/final_model/gated_lora_config.pt | Other | 1.8 KB | ef9b75d6d4e4 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/final_model/gating_network.pt | Other | 13.9 MB | 9713b2767107 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/final_model/scheduler.pt | Other | 1.7 KB | 4b13ed54111b |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/visualizations/exp4_gated_loadbalancing_seed1_entropy_per_layer.png | Other | 42.6 KB | da4c17ec4950 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/visualizations/exp4_gated_loadbalancing_seed1_layer_expert_heatmap.png | Other | 103.0 KB | 32107c170213 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/visualizations/exp4_gated_loadbalancing_seed1_task_expert_usage.png | Other | 43.1 KB | ce3cb96aa6d8 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/visualizations/exp4_gated_loadbalancing_seed1_token_routing_1.png | Other | 91.7 KB | f99c51f420b4 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/visualizations/exp4_gated_loadbalancing_seed1_token_routing_2.png | Other | 92.0 KB | e6aff1ea2de1 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed1/visualizations/exp4_gated_loadbalancing_seed1_token_routing_3.png | Other | 92.0 KB | 1373a22497ee |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/best_model/expert_pools.pt | Other | 16.7 MB | b9b6d28e140f |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/best_model/gated_lora_config.pt | Other | 1.8 KB | ef9b75d6d4e4 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/best_model/gating_network.pt | Other | 13.9 MB | 48220e22cfb5 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/best_model/scheduler.pt | Other | 1.7 KB | d5482a786682 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-1000/expert_pools.pt | Other | 16.7 MB | c24832e64282 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | ef9b75d6d4e4 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-1000/gating_network.pt | Other | 13.9 MB | 0814dc8f3735 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 0aea463251e0 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-1500/expert_pools.pt | Other | 16.7 MB | d757d85be3f3 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-1500/gated_lora_config.pt | Other | 1.8 KB | ef9b75d6d4e4 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-1500/gating_network.pt | Other | 13.9 MB | ae762074250e |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-1500/scheduler.pt | Other | 1.7 KB | ab65e3db4ba5 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-2000/expert_pools.pt | Other | 16.7 MB | 47b558d21d69 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-2000/gated_lora_config.pt | Other | 1.8 KB | ef9b75d6d4e4 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-2000/gating_network.pt | Other | 13.9 MB | be5a377a8d3d |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-2000/scheduler.pt | Other | 1.7 KB | 3b2455392db2 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-2500/expert_pools.pt | Other | 16.7 MB | bb2a22b88d16 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-2500/gated_lora_config.pt | Other | 1.8 KB | ef9b75d6d4e4 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-2500/gating_network.pt | Other | 13.9 MB | b113f0a06c87 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-2500/scheduler.pt | Other | 1.7 KB | 31bf47791394 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-3000/expert_pools.pt | Other | 16.7 MB | 305928d31ca9 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-3000/gated_lora_config.pt | Other | 1.8 KB | ef9b75d6d4e4 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-3000/gating_network.pt | Other | 13.9 MB | 83f7805fae07 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-3000/scheduler.pt | Other | 1.7 KB | 502043cb8756 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-3500/expert_pools.pt | Other | 16.7 MB | 122a85464203 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-3500/gated_lora_config.pt | Other | 1.8 KB | ef9b75d6d4e4 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-3500/gating_network.pt | Other | 13.9 MB | aa829d57953c |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-3500/scheduler.pt | Other | 1.7 KB | 2be695f86b21 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-4000/expert_pools.pt | Other | 16.7 MB | ebda6d66b8e8 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-4000/gated_lora_config.pt | Other | 1.8 KB | ef9b75d6d4e4 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-4000/gating_network.pt | Other | 13.9 MB | 139659c4510a |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-4000/scheduler.pt | Other | 1.7 KB | 673975514d3f |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-500/expert_pools.pt | Other | 16.7 MB | 2ce9a09d1981 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-500/gated_lora_config.pt | Other | 1.8 KB | ef9b75d6d4e4 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-500/gating_network.pt | Other | 13.9 MB | cb619da1110a |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/checkpoint-500/scheduler.pt | Other | 1.7 KB | 66c01bf5fb42 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/final_model/expert_pools.pt | Other | 16.7 MB | f2aa6a2a071a |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/final_model/gated_lora_config.pt | Other | 1.8 KB | ef9b75d6d4e4 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/final_model/gating_network.pt | Other | 13.9 MB | 81deebee4d4e |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/final_model/scheduler.pt | Other | 1.7 KB | 4b13ed54111b |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/visualizations/exp4_gated_loadbalancing_seed2_entropy_per_layer.png | Other | 42.1 KB | 3b2f249e50c6 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/visualizations/exp4_gated_loadbalancing_seed2_layer_expert_heatmap.png | Other | 103.0 KB | 1170691caf24 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/visualizations/exp4_gated_loadbalancing_seed2_task_expert_usage.png | Other | 43.0 KB | cedced771896 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/visualizations/exp4_gated_loadbalancing_seed2_token_routing_1.png | Other | 91.6 KB | 21a8ff423301 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/visualizations/exp4_gated_loadbalancing_seed2_token_routing_2.png | Other | 91.9 KB | ced767830165 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed2/visualizations/exp4_gated_loadbalancing_seed2_token_routing_3.png | Other | 92.0 KB | 1f043d999ce0 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed3/best_model/expert_pools.pt | Other | 16.7 MB | b6f3d6d5587f |
| legacy/pythia410m/exp4_gated_loadbalancing_seed3/best_model/gated_lora_config.pt | Other | 1.8 KB | ef9b75d6d4e4 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed3/best_model/gating_network.pt | Other | 13.9 MB | 10722d6ac1d5 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed3/best_model/scheduler.pt | Other | 1.7 KB | ab65e3db4ba5 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed3/checkpoint-1000/expert_pools.pt | Other | 16.7 MB | b051dfe69f7e |
| legacy/pythia410m/exp4_gated_loadbalancing_seed3/checkpoint-1000/gated_lora_config.pt | Other | 1.8 KB | ef9b75d6d4e4 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed3/checkpoint-1000/gating_network.pt | Other | 13.9 MB | e33eea659e71 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed3/checkpoint-1000/scheduler.pt | Other | 1.7 KB | 0aea463251e0 |
| legacy/pythia410m/exp4_gated_loadbalancing_seed3/checkpoint-1500/expert_pools.pt | Other | 16.7 MB | b6f3d6d5587f |
| .gitattributes | Repository | 2.8 KB | — |
| legacy/llama32/exp5_gated_topk_seed1/checkpoint-3500/.expert_pools.pt.O3Zbf8 | Repository | 30.9 MB | 8008cb13e625 |
License and Download
- License
- Not stated by the source
- Access
- No access gate
Released by Helain ZIMMERMANN through its official repository on Hugging Face.