Open-weight model
Qwen2.5-32B-graft0-a1-terra3k-r3000-da-e1
by SecondLookResearch SecondLookResearch/Qwen2.5-32B-graft0-a1-terra3k-r3000-da-e1
Qwen2.5-32B-graft0-a1-terra3k-r3000-da-e1 is an open-weight model from SecondLookResearch. Its published files total 2.2 GB.
Difficult advice (terra 3k ladder, rung 3000 rows), 1 epoch from scratch, fresh linear-only LoRA r64/a128 over frozen graft0-a1, warmup 5% (floor 2 steps). Rows are a seed-0 prefix of the same shuffle as the other rungs; val = terra3k-val-qwen25.jsonl.
Model Card
Difficult advice (terra 3k ladder, rung 3000 rows), 1 epoch from scratch, fresh linear-only LoRA r64/a128 over frozen graft0-a1, warmup 5% (floor 2 steps). Rows are a seed-0 prefix of the same shuffle as the other rungs; val = terra3k-val-qwen25.jsonl. LoRA r64/a128, linear-only, graft0 platform. Difficult-advice stage trained as a FRESH adapter over a merged, frozen A1. Serve as TWO adapters on the patched base, A1 first, then this one: ARM= ROWPATCH=1 ADAPTERS=" " \ bash code/msmeval/servereconstructed.sh
Excerpt from the card by SecondLookResearch.
Identity and Version
- Repository
- SecondLookResearch/Qwen2.5-32B-graft0-a1-terra3k-r3000-da-e1
- Publisher
- SecondLookResearch
- Task
- Not stated by the source
- Modality
- Other
- Library
- peft
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 2eccc5a678c12c7aa63cdfd20e4dc720e1bbcec3
- First published
- 2026-09-26
- Last updated
- 2026-09-26
Files and Weights
9 files, 2.2 GB in total. The weights are 3 files totalling 2.1 GB in bin, safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| adapter_model.safetensors | Weights | 2.1 GB | 42922b73d4c8 |
| base_row_patch.safetensors | Weights | 20.8 KB | db3baed66478 |
| training_args.bin | Weights | 5.8 KB | f69b2215fbe6 |
| adapter_config.json | Configuration | 1.1 KB | — |
| README.md | Documentation | 653 B | — |
| chat_template.jinja | Other | 370 B | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 11.4 MB | 3fd169731d2c |
| tokenizer_config.json | Tokenizer | 693 B | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 2.1 GB
Released by SecondLookResearch through its official repository on Hugging Face.
Built From
- Adapter of Qwen/Qwen2.5-32B
- Derived from Qwen/Qwen2.5-32B
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 2.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.