cap-evolve-ckpt-20260920 is an open-weight model from Yuanlin Duan. Its published files total 4.1 TB.
Parameters—
Context—
Weights4.1 TB
License—
AccessOpen weights
Monthly Downloads—
Model Card
The publisher has not written a card for this model.
Identity and Version
- Repository
- Yusubuda/cap-evolve-ckpt-20260920
- Publisher
- Yuanlin Duan
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 59f36bbeaeaf4abda05c4e8d97ae670812b13ecd
- First published
- 2026-09-20
- Last updated
- 2026-09-25
Files and Weights
2,170 files, 4.1 TB in total. The weights are 764 files totalling 4.1 TB in pt, safetensors.
Weights764 files · 4.1 TB
Configuration616 files · 25.8 MB
Tokenizer528 files · 2.1 GB
Other261 files · 14.1 GB
Repository1 file · 14.9 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| checkpoints/grpo_qwen3-4b_d2skill_base/global_step_10/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | f1432a472726 |
| checkpoints/grpo_qwen3-4b_d2skill_base/global_step_10/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | 86e013aa76b7 |
| checkpoints/grpo_qwen3-4b_d2skill_base/global_step_10/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | a9523f47ecce |
| checkpoints/grpo_qwen3-4b_d2skill_base/global_step_10/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | 33fd975518c7 |
| checkpoints/grpo_qwen3-4b_d2skill_base/global_step_10/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | 5cef9c80cc27 |
| checkpoints/grpo_qwen3-4b_d2skill_base/global_step_10/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | c442deeb1bb9 |
| checkpoints/grpo_qwen3-4b_d2skill_base/global_step_10/data.pt | Weights | 1.9 KB | 6e9a959aa893 |
| checkpoints/grpo_qwen3-4b_d2skill_sft/best_ckpt_step40/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 0a61cd794f63 |
| checkpoints/grpo_qwen3-4b_d2skill_sft/best_ckpt_step40/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | 228decfdab68 |
| checkpoints/grpo_qwen3-4b_d2skill_sft/best_ckpt_step40/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | c8da282fdc00 |
| checkpoints/grpo_qwen3-4b_d2skill_sft/best_ckpt_step40/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | 289fb52ed6c4 |
| checkpoints/grpo_qwen3-4b_d2skill_sft/best_ckpt_step40/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | aef33ea5c93d |
| checkpoints/grpo_qwen3-4b_d2skill_sft/best_ckpt_step40/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 895c6dc85540 |
| checkpoints/grpo_qwen3-4b_d2skill_sft/best_ckpt_step40/data.pt | Weights | 1.9 KB | 8b0403568fe7 |
| checkpoints/grpo_qwen3-4b_d2skill_sft/global_step_30/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | e04376e19fc0 |
| checkpoints/grpo_qwen3-4b_d2skill_sft/global_step_30/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | 957890d9a200 |
| checkpoints/grpo_qwen3-4b_d2skill_sft/global_step_30/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | ad6b1e93387d |
| checkpoints/grpo_qwen3-4b_d2skill_sft/global_step_30/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | 09fcfe0bce0f |
| checkpoints/grpo_qwen3-4b_d2skill_sft/global_step_30/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | 1898fdf02f98 |
| checkpoints/grpo_qwen3-4b_d2skill_sft/global_step_30/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 654fea9dbdc9 |
| checkpoints/grpo_qwen3-4b_d2skill_sft/global_step_30/data.pt | Weights | 1.9 KB | f569ef3ba96b |
| checkpoints/grpo_qwen3-4b_d2skill_sft/global_step_80/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 80f96e27023d |
| checkpoints/grpo_qwen3-4b_d2skill_sft/global_step_80/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | 1f3af03a4f27 |
| checkpoints/grpo_qwen3-4b_d2skill_sft/global_step_80/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | 175c10c4beef |
| checkpoints/grpo_qwen3-4b_d2skill_sft/global_step_80/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | be92ca2ab183 |
| checkpoints/grpo_qwen3-4b_d2skill_sft/global_step_80/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | 4be2eb1a5b95 |
| checkpoints/grpo_qwen3-4b_d2skill_sft/global_step_80/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 829ab22a124f |
| checkpoints/grpo_qwen3-4b_d2skill_sft/global_step_80/data.pt | Weights | 1.9 KB | 0c4e08faf25a |
| checkpoints/grpo_qwen3-4b_v6/global_step_160/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 78d1a1ff7bec |
| checkpoints/grpo_qwen3-4b_v6/global_step_160/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | d22b882a0d6b |
| checkpoints/grpo_qwen3-4b_v6/global_step_160/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | 231799672160 |
| checkpoints/grpo_qwen3-4b_v6/global_step_160/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | 349dbd592b20 |
| checkpoints/grpo_qwen3-4b_v6/global_step_160/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | c8fc9712a247 |
| checkpoints/grpo_qwen3-4b_v6/global_step_160/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | f2d5329c7bb2 |
| checkpoints/grpo_qwen3-4b_v6/global_step_160/data.pt | Weights | 1.9 KB | 3386aee7aa6c |
| checkpoints/grpo_qwen3-4b_v6_2/global_step_50/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 84e6ad06dcc0 |
| checkpoints/grpo_qwen3-4b_v6_2/global_step_50/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | a3e5c42acc2f |
| checkpoints/grpo_qwen3-4b_v6_2/global_step_50/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | 07c5019ea16a |
| checkpoints/grpo_qwen3-4b_v6_2/global_step_50/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | d1bbecb24578 |
| checkpoints/grpo_qwen3-4b_v6_2/global_step_50/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | 9108829f3558 |
| checkpoints/grpo_qwen3-4b_v6_2/global_step_50/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | d97cfbc8828d |
| checkpoints/grpo_qwen3-4b_v6_2/global_step_50/data.pt | Weights | 1.9 KB | 3fbba916b195 |
| checkpoints/grpo_qwen3-4b_v6_2_sft/global_step_90/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 67c8a6a6828e |
| checkpoints/grpo_qwen3-4b_v6_2_sft/global_step_90/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | 929b55be869a |
| checkpoints/grpo_qwen3-4b_v6_2_sft/global_step_90/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | 795f694f7159 |
| checkpoints/grpo_qwen3-4b_v6_2_sft/global_step_90/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | dd2fc6197002 |
| checkpoints/grpo_qwen3-4b_v6_2_sft/global_step_90/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | 11bf0faa547c |
| checkpoints/grpo_qwen3-4b_v6_2_sft/global_step_90/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 22caa2af70d8 |
| checkpoints/grpo_qwen3-4b_v6_2_sft/global_step_90/data.pt | Weights | 1.9 KB | 367852ff9b4b |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s123/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | d5a3d9fb7e5c |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s123/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | 47d298906178 |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s123/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | e76bf486f71b |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s123/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | ae35a65cb56e |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s123/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | 617464dbb30c |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s123/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | ce62ef27dcfc |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s123/data.pt | Weights | 1.9 KB | 5ba906990019 |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s30/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | e04376e19fc0 |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s30/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | 957890d9a200 |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s30/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | f48ded93c648 |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s30/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | 4382623a7ce4 |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s30/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | 8b95be97a0ab |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s30/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 0d149d4d65b4 |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s30/data.pt | Weights | 1.9 KB | acfc207b6d7f |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s40/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 0a61cd794f63 |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s40/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | 228decfdab68 |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s40/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | 4f3f2b3f72d2 |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s40/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | 1a43965bba9b |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s40/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | 05c046ae78da |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s40/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 1d1bdb80de59 |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s40/data.pt | Weights | 1.9 KB | 9d7d4f39ee47 |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s80/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 80f96e27023d |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s80/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | 1f3af03a4f27 |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s80/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | bcb06e392fda |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s80/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | 98b06ae10e46 |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s80/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | 281605516961 |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s80/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 3ec96b0a01bb |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s80/data.pt | Weights | 1.9 KB | 4d40249a0382 |
| grpo_qwen3-4b_appworld_grpo_base/best/model-00001-of-00002.safetensors | Weights | 5.0 GB | 8950ffbcaef9 |
| grpo_qwen3-4b_appworld_grpo_base/best/model-00002-of-00002.safetensors | Weights | 3.8 GB | 0168e37de302 |
| grpo_qwen3-4b_appworld_grpo_base/latest/model-00001-of-00002.safetensors | Weights | 5.0 GB | 39a033c0f59a |
| grpo_qwen3-4b_appworld_grpo_base/latest/model-00002-of-00002.safetensors | Weights | 3.9 GB | f6bb1f37e2fe |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s129/model-00001-of-00002.safetensors | Weights | 5.0 GB | bf04e76baf1b |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s129/model-00002-of-00002.safetensors | Weights | 3.8 GB | 21263ac98607 |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s130/model-00001-of-00002.safetensors | Weights | 5.0 GB | cd20a0b5c611 |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s130/model-00002-of-00002.safetensors | Weights | 3.9 GB | ba744a5edf5a |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s95/model-00001-of-00002.safetensors | Weights | 5.0 GB | 8950ffbcaef9 |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s95/model-00002-of-00002.safetensors | Weights | 3.8 GB | 0168e37de302 |
| grpo_qwen3-4b_appworld_skillrl_flash/anchor_s30/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | e04376e19fc0 |
| grpo_qwen3-4b_appworld_skillrl_flash/anchor_s30/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | 957890d9a200 |
| grpo_qwen3-4b_appworld_skillrl_flash/anchor_s30/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | 07d0dc453134 |
| grpo_qwen3-4b_appworld_skillrl_flash/anchor_s30/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | f4fcf8e46c51 |
| grpo_qwen3-4b_appworld_skillrl_flash/anchor_s30/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | 3c818784ccc5 |
| grpo_qwen3-4b_appworld_skillrl_flash/anchor_s30/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 18c04b3cc33a |
| grpo_qwen3-4b_appworld_skillrl_flash/anchor_s30/data.pt | Weights | 1.9 KB | 1f163a4e4e75 |
| grpo_qwen3-4b_appworld_skillrl_flash/anchor_s90/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 67c8a6a6828e |
| grpo_qwen3-4b_appworld_skillrl_flash/anchor_s90/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | 929b55be869a |
| grpo_qwen3-4b_appworld_skillrl_flash/anchor_s90/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | 647295b61d15 |
| grpo_qwen3-4b_appworld_skillrl_flash/anchor_s90/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | 2a861e724815 |
| grpo_qwen3-4b_appworld_skillrl_flash/anchor_s90/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | 6dd52f9eab51 |
| grpo_qwen3-4b_appworld_skillrl_flash/anchor_s90/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | f30112fbcb54 |
| grpo_qwen3-4b_appworld_skillrl_flash/anchor_s90/data.pt | Weights | 1.9 KB | 002952c45a7e |
| grpo_qwen3-4b_appworld_skillrl_flash/best/model-00001-of-00002.safetensors | Weights | 4.2 GB | b681b9c1f0dc |
| grpo_qwen3-4b_appworld_skillrl_flash/best/model-00002-of-00002.safetensors | Weights | 4.6 GB | 0eb531ff7743 |
| grpo_qwen3-4b_appworld_skillrl_flash/latest/model-00001-of-00002.safetensors | Weights | 5.0 GB | 2b965151209d |
| grpo_qwen3-4b_appworld_skillrl_flash/latest/model-00002-of-00002.safetensors | Weights | 3.8 GB | b2fb80600047 |
| grpo_qwen3-4b_appworld_skillrl_flash/rescued_s95/model-00001-of-00002.safetensors | Weights | 4.2 GB | b681b9c1f0dc |
| grpo_qwen3-4b_appworld_skillrl_flash/rescued_s95/model-00002-of-00002.safetensors | Weights | 4.6 GB | 0eb531ff7743 |
| grpo_qwen3-4b_appworld_skillrl_luna/anchor_s30/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | e04376e19fc0 |
| grpo_qwen3-4b_appworld_skillrl_luna/anchor_s30/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | 957890d9a200 |
| grpo_qwen3-4b_appworld_skillrl_luna/anchor_s30/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | fb7696accac1 |
| grpo_qwen3-4b_appworld_skillrl_luna/anchor_s30/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | 7b62acdffbcc |
| grpo_qwen3-4b_appworld_skillrl_luna/anchor_s30/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | 873603243da2 |
| grpo_qwen3-4b_appworld_skillrl_luna/anchor_s30/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 27208d39ca9c |
| grpo_qwen3-4b_appworld_skillrl_luna/anchor_s30/data.pt | Weights | 1.9 KB | 9028f266517e |
| grpo_qwen3-4b_appworld_skillrl_luna/anchor_s95/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 20c2322142b0 |
| grpo_qwen3-4b_appworld_skillrl_luna/anchor_s95/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | b560496fc12a |
| grpo_qwen3-4b_appworld_skillrl_luna/anchor_s95/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | 77015fd6b30f |
| grpo_qwen3-4b_appworld_skillrl_luna/anchor_s95/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | ea669316eac3 |
| grpo_qwen3-4b_appworld_skillrl_luna/anchor_s95/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | 4118e2d97c85 |
| grpo_qwen3-4b_appworld_skillrl_luna/anchor_s95/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 22b4b04d059a |
| grpo_qwen3-4b_appworld_skillrl_luna/anchor_s95/data.pt | Weights | 1.9 KB | 2402f0ee803c |
| grpo_qwen3-4b_appworld_skillrl_luna/best/model-00001-of-00002.safetensors | Weights | 5.0 GB | 53376d93573a |
| grpo_qwen3-4b_appworld_skillrl_luna/best/model-00002-of-00002.safetensors | Weights | 3.8 GB | f3fe22a38828 |
| grpo_qwen3-4b_appworld_skillrl_luna/latest/model-00001-of-00002.safetensors | Weights | 5.0 GB | 475b019f686b |
| grpo_qwen3-4b_appworld_skillrl_luna/latest/model-00002-of-00002.safetensors | Weights | 3.8 GB | 1679b6ca7119 |
| grpo_qwen3-4b_appworld_skillrl_luna/rescued_s65/model-00001-of-00002.safetensors | Weights | 5.0 GB | 53376d93573a |
| grpo_qwen3-4b_appworld_skillrl_luna/rescued_s65/model-00002-of-00002.safetensors | Weights | 3.8 GB | f3fe22a38828 |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s30/actor/extra_state_world_size_4_rank_0.pt | Weights | 15.1 KB | e083aca7e46f |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s30/actor/extra_state_world_size_4_rank_1.pt | Weights | 15.1 KB | 8df53b08e0f4 |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s30/actor/extra_state_world_size_4_rank_2.pt | Weights | 15.1 KB | b619e1415c7f |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s30/actor/extra_state_world_size_4_rank_3.pt | Weights | 15.1 KB | cc9f1af2c732 |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s30/actor/model_world_size_4_rank_0.pt | Weights | 4.4 GB | dab7a4333622 |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s30/actor/model_world_size_4_rank_1.pt | Weights | 4.4 GB | 8731bb29e40b |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s30/actor/model_world_size_4_rank_2.pt | Weights | 4.4 GB | 84e1dd1f136e |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s30/actor/model_world_size_4_rank_3.pt | Weights | 4.4 GB | dfea546e243a |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s30/actor/optim_world_size_4_rank_0.pt | Weights | 8.0 GB | ed644db5b314 |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s30/actor/optim_world_size_4_rank_1.pt | Weights | 8.0 GB | 0299f1e5a98a |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s30/actor/optim_world_size_4_rank_2.pt | Weights | 8.0 GB | 68b2d3e6c94b |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s30/actor/optim_world_size_4_rank_3.pt | Weights | 8.0 GB | 3d3fc909023b |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s30/data.pt | Weights | 1.9 KB | c5097723b079 |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s90/actor/extra_state_world_size_4_rank_0.pt | Weights | 15.1 KB | 7f28bc9fd5cf |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s90/actor/extra_state_world_size_4_rank_1.pt | Weights | 15.1 KB | 0eae9f56ecc9 |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s90/actor/extra_state_world_size_4_rank_2.pt | Weights | 15.1 KB | 67af24b96a23 |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s90/actor/extra_state_world_size_4_rank_3.pt | Weights | 15.1 KB | dde356f4f954 |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s90/actor/model_world_size_4_rank_0.pt | Weights | 4.4 GB | 7cb066c6d7a0 |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s90/actor/model_world_size_4_rank_1.pt | Weights | 4.4 GB | 23d45a45334a |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s90/actor/model_world_size_4_rank_2.pt | Weights | 4.4 GB | 04bd4036637c |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s90/actor/model_world_size_4_rank_3.pt | Weights | 4.4 GB | 257060106e23 |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s90/actor/optim_world_size_4_rank_0.pt | Weights | 8.0 GB | 4228a97fd6b2 |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s90/actor/optim_world_size_4_rank_1.pt | Weights | 8.0 GB | d30e3c1f8089 |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s90/actor/optim_world_size_4_rank_2.pt | Weights | 8.0 GB | 015b8124cb6d |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s90/actor/optim_world_size_4_rank_3.pt | Weights | 8.0 GB | efc21cb1f5a8 |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s90/data.pt | Weights | 1.9 KB | 2d4993e336d9 |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s96/actor/extra_state_world_size_4_rank_0.pt | Weights | 15.1 KB | d0189b26db07 |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s96/actor/extra_state_world_size_4_rank_1.pt | Weights | 15.1 KB | 2f8c00dafc0d |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s96/actor/extra_state_world_size_4_rank_2.pt | Weights | 15.1 KB | 925996ef9af9 |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s96/actor/extra_state_world_size_4_rank_3.pt | Weights | 15.1 KB | 67a6c802087e |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s96/actor/model_world_size_4_rank_0.pt | Weights | 4.4 GB | 9b10aacb002a |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s96/actor/model_world_size_4_rank_1.pt | Weights | 4.4 GB | d51c0d286a94 |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s96/actor/model_world_size_4_rank_2.pt | Weights | 4.4 GB | f23a4f90c3ba |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s96/actor/model_world_size_4_rank_3.pt | Weights | 4.4 GB | ad155b81c5d9 |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s96/actor/optim_world_size_4_rank_0.pt | Weights | 8.0 GB | b4b7912aff23 |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s96/actor/optim_world_size_4_rank_1.pt | Weights | 8.0 GB | 928031951a43 |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s96/actor/optim_world_size_4_rank_2.pt | Weights | 8.0 GB | 7eccad2b274b |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s96/actor/optim_world_size_4_rank_3.pt | Weights | 8.0 GB | a815520f1c03 |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s96/data.pt | Weights | 1.9 KB | b3932dd7f9ab |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/best/model-00001-of-00002.safetensors | Weights | 4.7 GB | 54d40fc699f7 |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/best/model-00002-of-00002.safetensors | Weights | 4.1 GB | d506b09103f8 |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/latest/model-00001-of-00002.safetensors | Weights | 5.0 GB | a721971411b4 |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/latest/model-00002-of-00002.safetensors | Weights | 3.8 GB | 33ec533762ce |
| grpo_qwen3-4b_appworld_skillrl_luna_sft_2gpu_run_s5/anchor_s5/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 521df92ec306 |
| grpo_qwen3-4b_appworld_skillrl_luna_sft_2gpu_run_s5/anchor_s5/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | c5e7fc907254 |
| grpo_qwen3-4b_appworld_skillrl_luna_sft_2gpu_run_s5/anchor_s5/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | 1dd04af414c1 |
| grpo_qwen3-4b_appworld_skillrl_luna_sft_2gpu_run_s5/anchor_s5/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | dbdbb962872e |
| grpo_qwen3-4b_appworld_skillrl_luna_sft_2gpu_run_s5/anchor_s5/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | b6525e827a88 |
| grpo_qwen3-4b_appworld_skillrl_luna_sft_2gpu_run_s5/anchor_s5/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 4f097115271b |
| grpo_qwen3-4b_appworld_skillrl_luna_sft_2gpu_run_s5/anchor_s5/data.pt | Weights | 1.9 KB | ee99ac8a40c7 |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s30/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | e04376e19fc0 |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s30/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | 957890d9a200 |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s30/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | 75ebc4857086 |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s30/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | 751248ed6bd8 |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s30/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | 1b601460a6c9 |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s30/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 33df536f7f30 |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s30/data.pt | Weights | 1.9 KB | a68f43164b2e |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s68/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 3ebdd6ee2d89 |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s68/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | d4b73dc6747e |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s68/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | 9a4d95a1cc1e |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s68/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | ac48ab13a241 |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s68/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | d052edcb9e97 |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s68/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 791ddffbce07 |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s68/data.pt | Weights | 1.9 KB | 017017838c69 |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s80/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 80f96e27023d |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s80/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | 1f3af03a4f27 |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s80/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | 708a84bbb1c1 |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s80/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | 0f49e319ee0f |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s80/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | bb9d44a6398e |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s80/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | cda2a4b38f1c |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s80/data.pt | Weights | 1.9 KB | f3cfc353f8e1 |
| grpo_qwen3-4b_d2skill_appworld_flash/best/model-00001-of-00002.safetensors | Weights | 5.0 GB | 4e1483774088 |
| grpo_qwen3-4b_d2skill_appworld_flash/best/model-00002-of-00002.safetensors | Weights | 3.9 GB | 0af8fa18495b |
| grpo_qwen3-4b_d2skill_appworld_flash/latest/model-00001-of-00002.safetensors | Weights | 5.0 GB | 56c07ccf25aa |
| grpo_qwen3-4b_d2skill_appworld_flash/latest/model-00002-of-00002.safetensors | Weights | 3.8 GB | 4bbe7bb4697f |
| grpo_qwen3-4b_d2skill_appworld_flash/rescued_s50/model-00001-of-00002.safetensors | Weights | 5.0 GB | 4e1483774088 |
| grpo_qwen3-4b_d2skill_appworld_flash/rescued_s50/model-00002-of-00002.safetensors | Weights | 3.9 GB | 0af8fa18495b |
| grpo_qwen3-4b_d2skill_appworld_flash/rescued_s72/model-00001-of-00002.safetensors | Weights | 5.0 GB | c33d796858c5 |
| grpo_qwen3-4b_d2skill_appworld_flash/rescued_s72/model-00002-of-00002.safetensors | Weights | 3.8 GB | ed2ddbd29a96 |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s30/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | e04376e19fc0 |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s30/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | 957890d9a200 |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s30/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | 88e65f2d20a2 |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s30/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | 165d4759dac8 |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s30/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | c949aa44b3fa |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s30/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | c77be8303005 |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s30/data.pt | Weights | 1.9 KB | bf75b37af860 |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s80/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 80f96e27023d |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s80/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | 1f3af03a4f27 |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s80/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | 2b446eeae947 |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s80/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | a22d30b4ae8c |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s80/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | f1f483e3c179 |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s80/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 07e4bc1bee57 |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s80/data.pt | Weights | 1.9 KB | b5a4ad958646 |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s85/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | a098d8d0e0b8 |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s85/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | ebe5847b9ea3 |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s85/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | 35469cecc7d7 |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s85/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | 4d4e9ae60ca2 |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s85/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | 8c2f6473064f |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s85/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | cd0c8d164a94 |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s85/data.pt | Weights | 1.9 KB | 9007a667f61c |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s89/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 2185f07801c2 |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s89/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | 400aa8218c04 |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s89/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | c7e14e2d58a9 |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s89/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | bb7cedbacd3b |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s89/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | ddc0d61eda35 |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s89/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 07b7a55f6d57 |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s89/data.pt | Weights | 1.9 KB | d75d45bb1935 |
| grpo_qwen3-4b_d2skill_appworld_luna/best/model-00001-of-00002.safetensors | Weights | 5.0 GB | aa23cc6ffdff |
| grpo_qwen3-4b_d2skill_appworld_luna/best/model-00002-of-00002.safetensors | Weights | 3.8 GB | d76193dedecb |
| grpo_qwen3-4b_d2skill_appworld_luna/best_s70/model-00001-of-00002.safetensors | Weights | 5.0 GB | a0a7c707f93e |
| grpo_qwen3-4b_d2skill_appworld_luna/best_s70/model-00002-of-00002.safetensors | Weights | 3.8 GB | 3eed1ba9ba90 |
| grpo_qwen3-4b_d2skill_appworld_luna/latest/model-00001-of-00002.safetensors | Weights | 5.0 GB | 42af3a705600 |
| grpo_qwen3-4b_d2skill_appworld_luna/latest/model-00002-of-00002.safetensors | Weights | 3.9 GB | acbdf066ab9f |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/actor/extra_state_world_size_8_rank_0.pt | Weights | 15.1 KB | 33032ddf95df |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/actor/extra_state_world_size_8_rank_1.pt | Weights | 15.1 KB | f3af44aace9a |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/actor/extra_state_world_size_8_rank_2.pt | Weights | 15.1 KB | ba1cd16d55b2 |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/actor/extra_state_world_size_8_rank_3.pt | Weights | 15.1 KB | 6fb03a90793b |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/actor/extra_state_world_size_8_rank_4.pt | Weights | 15.1 KB | dbfd43398401 |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/actor/extra_state_world_size_8_rank_5.pt | Weights | 15.1 KB | dd7f147d19d9 |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/actor/extra_state_world_size_8_rank_6.pt | Weights | 15.1 KB | 82c7bb878f84 |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/actor/extra_state_world_size_8_rank_7.pt | Weights | 15.1 KB | 7bb6f06e0532 |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/actor/model_world_size_8_rank_0.pt | Weights | 2.2 GB | 57c3a78907a1 |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/actor/model_world_size_8_rank_1.pt | Weights | 2.2 GB | 982f20d494be |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/actor/model_world_size_8_rank_2.pt | Weights | 2.2 GB | d1eb101b4073 |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/actor/model_world_size_8_rank_3.pt | Weights | 2.2 GB | 5755a20e8f73 |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/actor/model_world_size_8_rank_4.pt | Weights | 2.2 GB | b63439146fa5 |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/actor/model_world_size_8_rank_5.pt | Weights | 2.2 GB | 7c2c31ed0492 |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/actor/model_world_size_8_rank_6.pt | Weights | 2.2 GB | 98a45e494df8 |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/actor/model_world_size_8_rank_7.pt | Weights | 2.2 GB | 9d0f1adde996 |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/actor/optim_world_size_8_rank_0.pt | Weights | 4.0 GB | 3bbff32b1e99 |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/actor/optim_world_size_8_rank_1.pt | Weights | 4.0 GB | 8f02c5c3053c |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/actor/optim_world_size_8_rank_2.pt | Weights | 4.0 GB | 15a6ba7ddcaa |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/actor/optim_world_size_8_rank_3.pt | Weights | 4.0 GB | 57e55846b4e3 |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/actor/optim_world_size_8_rank_4.pt | Weights | 4.0 GB | c6c3bde360b6 |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/actor/optim_world_size_8_rank_5.pt | Weights | 4.0 GB | fead344f46b0 |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/actor/optim_world_size_8_rank_6.pt | Weights | 4.0 GB | 4651d5ad7988 |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/actor/optim_world_size_8_rank_7.pt | Weights | 4.0 GB | a44ec9a1d62a |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/data.pt | Weights | 1.9 KB | 62da2b755841 |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/best/model-00001-of-00002.safetensors | Weights | 5.0 GB | 559807d7db0f |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/best/model-00002-of-00002.safetensors | Weights | 3.8 GB | 85bc8d737b8c |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/latest/model-00001-of-00002.safetensors | Weights | 5.0 GB | 88c3f0876368 |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/latest/model-00002-of-00002.safetensors | Weights | 3.8 GB | d80c3f6c13f8 |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/rescued_s23/model-00001-of-00002.safetensors | Weights | 5.0 GB | 559807d7db0f |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/rescued_s23/model-00002-of-00002.safetensors | Weights | 3.8 GB | 85bc8d737b8c |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__2gpu_run_s5/anchor_s5/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 521df92ec306 |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__2gpu_run_s5/anchor_s5/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | c5e7fc907254 |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__2gpu_run_s5/anchor_s5/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | cf06e78344a1 |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__2gpu_run_s5/anchor_s5/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | 351d333b7238 |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__2gpu_run_s5/anchor_s5/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | 84de2e29d84f |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__2gpu_run_s5/anchor_s5/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 237bba582095 |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__2gpu_run_s5/anchor_s5/data.pt | Weights | 1.9 KB | 467b92fe86cb |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__4gpu_run_s5/anchor_s5/actor/extra_state_world_size_4_rank_0.pt | Weights | 15.1 KB | 57ada993e77b |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__4gpu_run_s5/anchor_s5/actor/extra_state_world_size_4_rank_1.pt | Weights | 15.1 KB | 4941ad390533 |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__4gpu_run_s5/anchor_s5/actor/extra_state_world_size_4_rank_2.pt | Weights | 15.1 KB | 187fdde5d4a6 |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__4gpu_run_s5/anchor_s5/actor/extra_state_world_size_4_rank_3.pt | Weights | 15.1 KB | eb9ae005671b |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__4gpu_run_s5/anchor_s5/actor/model_world_size_4_rank_0.pt | Weights | 4.4 GB | 05dea1db6a09 |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__4gpu_run_s5/anchor_s5/actor/model_world_size_4_rank_1.pt | Weights | 4.4 GB | c6051f7f9c60 |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__4gpu_run_s5/anchor_s5/actor/model_world_size_4_rank_2.pt | Weights | 4.4 GB | 70cd955ca0b6 |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__4gpu_run_s5/anchor_s5/actor/model_world_size_4_rank_3.pt | Weights | 4.4 GB | 6e6e4677cd8f |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__4gpu_run_s5/anchor_s5/actor/optim_world_size_4_rank_0.pt | Weights | 8.0 GB | bbb1ebc77422 |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__4gpu_run_s5/anchor_s5/actor/optim_world_size_4_rank_1.pt | Weights | 8.0 GB | 2408f87dc814 |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__4gpu_run_s5/anchor_s5/actor/optim_world_size_4_rank_2.pt | Weights | 8.0 GB | cb6973050e01 |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__4gpu_run_s5/anchor_s5/actor/optim_world_size_4_rank_3.pt | Weights | 8.0 GB | 5f4f34bbfb48 |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__4gpu_run_s5/anchor_s5/data.pt | Weights | 1.9 KB | 770a1eed3d0f |
| grpo_qwen3-4b_d2skill_base/anchor_s120/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | d03ce23d4f8f |
| grpo_qwen3-4b_d2skill_base/anchor_s120/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | 9dac9a622e88 |
| grpo_qwen3-4b_d2skill_base/anchor_s120/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | cfc6e7f0704d |
| grpo_qwen3-4b_d2skill_base/anchor_s120/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | 1ab9d0a16e88 |
| grpo_qwen3-4b_d2skill_base/anchor_s120/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | 7682f17f5ec0 |
| grpo_qwen3-4b_d2skill_base/anchor_s120/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | c9149ae2ac2a |
| grpo_qwen3-4b_d2skill_base/anchor_s120/data.pt | Weights | 1.9 KB | fbf5b9717904 |
| grpo_qwen3-4b_d2skill_base/anchor_s160/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 78d1a1ff7bec |
| grpo_qwen3-4b_d2skill_base/anchor_s160/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | d22b882a0d6b |
| grpo_qwen3-4b_d2skill_base/anchor_s160/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | cb3c38dddc12 |
| grpo_qwen3-4b_d2skill_base/anchor_s160/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | cbdbda7f1088 |
| grpo_qwen3-4b_d2skill_base/anchor_s160/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | d96da488040b |
| grpo_qwen3-4b_d2skill_base/anchor_s160/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 2d94d1a0c86b |
| grpo_qwen3-4b_d2skill_base/anchor_s160/data.pt | Weights | 1.9 KB | eae7fbee9dff |
| grpo_qwen3-4b_d2skill_base/best/model-00001-of-00002.safetensors | Weights | 5.0 GB | 6fae2fadf0a9 |
| grpo_qwen3-4b_d2skill_base/best/model-00002-of-00002.safetensors | Weights | 3.8 GB | 821895e798a4 |
| grpo_qwen3-4b_d2skill_base/latest/model-00001-of-00002.safetensors | Weights | 4.9 GB | 3e2cc45b68c9 |
| grpo_qwen3-4b_d2skill_base/latest/model-00002-of-00002.safetensors | Weights | 3.9 GB | 2cb7b432b87f |
| grpo_qwen3-4b_d2skill_base/rescued_s135/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 81edb4fb0b4e |
| grpo_qwen3-4b_d2skill_base/rescued_s135/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | 0cef3031f39e |
| grpo_qwen3-4b_d2skill_base/rescued_s135/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | a8e0ba3cfe7d |
| grpo_qwen3-4b_d2skill_base/rescued_s135/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | f8f1b429eae3 |
| grpo_qwen3-4b_d2skill_base/rescued_s135/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | c7cf8f086ff7 |
| grpo_qwen3-4b_d2skill_base/rescued_s135/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | f5be2e8d17af |
| grpo_qwen3-4b_d2skill_base/rescued_s135/data.pt | Weights | 1.9 KB | 9ead9ff02e22 |
| grpo_qwen3-4b_d2skill_base/rescued_s160/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 78d1a1ff7bec |
| grpo_qwen3-4b_d2skill_base/rescued_s160/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | d22b882a0d6b |
| grpo_qwen3-4b_d2skill_base/rescued_s160/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | cb3c38dddc12 |
| grpo_qwen3-4b_d2skill_base/rescued_s160/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | cbdbda7f1088 |
| grpo_qwen3-4b_d2skill_base/rescued_s160/data.pt | Weights | 1.9 KB | eae7fbee9dff |
| grpo_qwen3-4b_d2skill_base/rescued_s85/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | a098d8d0e0b8 |
| grpo_qwen3-4b_d2skill_base/rescued_s85/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | ebe5847b9ea3 |
| grpo_qwen3-4b_d2skill_base/rescued_s85/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | ac81583ac119 |
| grpo_qwen3-4b_d2skill_base/rescued_s85/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | 096b1cdb232c |
| grpo_qwen3-4b_d2skill_base/rescued_s85/data.pt | Weights | 1.9 KB | cd456429cb9a |
| grpo_qwen3-4b_d2skill_sft/best/model-00001-of-00002.safetensors | Weights | 5.0 GB | ec248d279d17 |
| grpo_qwen3-4b_d2skill_sft/best/model-00002-of-00002.safetensors | Weights | 3.9 GB | 3f18fc3c8199 |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s155/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 21123986e18d |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s155/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | 7c56cbfa3720 |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s155/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | 9525af9b331c |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s155/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | 22a436b3fd00 |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s155/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | c4531f459501 |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s155/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 24078f99a83f |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s155/data.pt | Weights | 1.9 KB | 8d4d63efa494 |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s160/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 78d1a1ff7bec |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s160/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | d22b882a0d6b |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s160/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | b8f83f369139 |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s160/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | 966afc516c2b |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s160/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | a4232eab5f0e |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s160/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 72f7d16ac064 |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s160/data.pt | Weights | 1.9 KB | 4f81ecf98219 |
| grpo_qwen3-4b_d2skill_sft_b80/best/model-00001-of-00002.safetensors | Weights | 5.0 GB | 0082952860ae |
| grpo_qwen3-4b_d2skill_sft_b80/best/model-00002-of-00002.safetensors | Weights | 3.8 GB | 6268d4062925 |
| grpo_qwen3-4b_d2skill_sft_b80/latest/model-00001-of-00002.safetensors | Weights | 5.0 GB | 7a9579a055e5 |
| grpo_qwen3-4b_d2skill_sft_b80/latest/model-00002-of-00002.safetensors | Weights | 3.8 GB | 0b1516c98ef2 |
| grpo_qwen3-4b_gem_d2skill/anchor_s155/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 21123986e18d |
| grpo_qwen3-4b_gem_d2skill/anchor_s155/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | 7c56cbfa3720 |
| grpo_qwen3-4b_gem_d2skill/anchor_s155/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | 396fb3a19417 |
| grpo_qwen3-4b_gem_d2skill/anchor_s155/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | 18d7bba95964 |
| grpo_qwen3-4b_gem_d2skill/anchor_s155/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | c024a8854052 |
| grpo_qwen3-4b_gem_d2skill/anchor_s155/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 611c1ac9ba98 |
| grpo_qwen3-4b_gem_d2skill/anchor_s155/data.pt | Weights | 1.9 KB | 96369f74a6aa |
| grpo_qwen3-4b_gem_d2skill/anchor_s160/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 78d1a1ff7bec |
| grpo_qwen3-4b_gem_d2skill/anchor_s160/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | d22b882a0d6b |
| grpo_qwen3-4b_gem_d2skill/anchor_s160/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | a3eece9232c9 |
| grpo_qwen3-4b_gem_d2skill/anchor_s160/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | c6149f757ac3 |
| grpo_qwen3-4b_gem_d2skill/anchor_s160/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | e4b2faa2791c |
| grpo_qwen3-4b_gem_d2skill/anchor_s160/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 027f0fd6d6b8 |
| grpo_qwen3-4b_gem_d2skill/anchor_s160/data.pt | Weights | 1.9 KB | 2d1096db4f5e |
| grpo_qwen3-4b_gem_d2skill/best/model-00001-of-00002.safetensors | Weights | 5.0 GB | 079359a20928 |
| grpo_qwen3-4b_gem_d2skill/best/model-00002-of-00002.safetensors | Weights | 3.8 GB | 17a02f644394 |
| grpo_qwen3-4b_gem_d2skill/latest/model-00001-of-00002.safetensors | Weights | 5.0 GB | c62ed788190f |
| grpo_qwen3-4b_gem_d2skill/latest/model-00002-of-00002.safetensors | Weights | 3.8 GB | ba8222fa5c93 |
| grpo_qwen3-4b_gem_d2skill/rescued_s130/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 52bf4b56ab56 |
| grpo_qwen3-4b_gem_d2skill/rescued_s130/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | 32a5649228cf |
| grpo_qwen3-4b_gem_d2skill/rescued_s130/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | bd5142e11944 |
| grpo_qwen3-4b_gem_d2skill/rescued_s130/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | fb8b89a203f2 |
| grpo_qwen3-4b_gem_d2skill/rescued_s130/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | e452fbd7da68 |
| grpo_qwen3-4b_gem_d2skill/rescued_s130/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 82cb73a43d16 |
| grpo_qwen3-4b_gem_d2skill/rescued_s130/data.pt | Weights | 1.9 KB | 43e432f0b8d6 |
| grpo_qwen3-4b_gem_v6_2/anchor_s160/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 78d1a1ff7bec |
| grpo_qwen3-4b_gem_v6_2/anchor_s160/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | d22b882a0d6b |
| grpo_qwen3-4b_gem_v6_2/anchor_s160/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | 6851e65994a1 |
| grpo_qwen3-4b_gem_v6_2/anchor_s160/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | 67ad15d63c6b |
| grpo_qwen3-4b_gem_v6_2/anchor_s160/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | b44ad95e60b2 |
| grpo_qwen3-4b_gem_v6_2/anchor_s160/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 22305703f104 |
| grpo_qwen3-4b_gem_v6_2/anchor_s160/data.pt | Weights | 1.9 KB | 33ccd73952fd |
| grpo_qwen3-4b_gem_v6_2/anchor_s170/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 9f839da8a233 |
| grpo_qwen3-4b_gem_v6_2/anchor_s170/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | dd4a2ca222cc |
| grpo_qwen3-4b_gem_v6_2/anchor_s170/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | f2068e0e8acc |
| grpo_qwen3-4b_gem_v6_2/anchor_s170/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | 3f311a3e4bbd |
| grpo_qwen3-4b_gem_v6_2/anchor_s170/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | 2d54b9ce3769 |
| grpo_qwen3-4b_gem_v6_2/anchor_s170/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 063119602219 |
| grpo_qwen3-4b_gem_v6_2/anchor_s170/data.pt | Weights | 1.9 KB | be9bcdecc519 |
| grpo_qwen3-4b_gem_v6_2/anchor_s40/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 0a61cd794f63 |
| grpo_qwen3-4b_gem_v6_2/anchor_s40/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | 228decfdab68 |
| grpo_qwen3-4b_gem_v6_2/anchor_s40/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | 841dbf4d10ab |
| grpo_qwen3-4b_gem_v6_2/anchor_s40/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | b1f74127da7e |
| grpo_qwen3-4b_gem_v6_2/anchor_s40/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | 37c33894692a |
| grpo_qwen3-4b_gem_v6_2/anchor_s40/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | b66f1a9bf8d8 |
| grpo_qwen3-4b_gem_v6_2/anchor_s40/data.pt | Weights | 1.9 KB | d25c97d1879a |
| grpo_qwen3-4b_gem_v6_2/best/model-00001-of-00002.safetensors | Weights | 5.0 GB | 8e8580d96a9d |
| grpo_qwen3-4b_gem_v6_2/best/model-00002-of-00002.safetensors | Weights | 3.8 GB | 6f8b7daced1f |
| grpo_qwen3-4b_gem_v6_2/latest/model-00001-of-00002.safetensors | Weights | 5.0 GB | e3ab0a6d21bd |
| grpo_qwen3-4b_gem_v6_2/latest/model-00002-of-00002.safetensors | Weights | 3.8 GB | 7381954fc4b0 |
| grpo_qwen3-4b_gem_v6_2/rescued_s120/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | d03ce23d4f8f |
| grpo_qwen3-4b_gem_v6_2/rescued_s120/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | 9dac9a622e88 |
| grpo_qwen3-4b_gem_v6_2/rescued_s120/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | 2323b49e9ca2 |
| grpo_qwen3-4b_gem_v6_2/rescued_s120/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | 1fdceead4d3e |
| grpo_qwen3-4b_gem_v6_2/rescued_s120/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | da16e713beeb |
| grpo_qwen3-4b_gem_v6_2/rescued_s120/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 7706063e0b46 |
| grpo_qwen3-4b_gem_v6_2/rescued_s120/data.pt | Weights | 1.9 KB | 8873e58f278a |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s100/actor/extra_state_world_size_4_rank_0.pt | Weights | 15.1 KB | bdfae3873750 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s100/actor/extra_state_world_size_4_rank_1.pt | Weights | 15.1 KB | 7e0937ade806 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s100/actor/extra_state_world_size_4_rank_2.pt | Weights | 15.1 KB | 18b377b6d782 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s100/actor/extra_state_world_size_4_rank_3.pt | Weights | 15.1 KB | aed674283cf2 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s100/actor/model_world_size_4_rank_0.pt | Weights | 4.4 GB | 992ca585a106 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s100/actor/model_world_size_4_rank_1.pt | Weights | 4.4 GB | 685022d46da2 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s100/actor/model_world_size_4_rank_2.pt | Weights | 4.4 GB | c19e6d3cb4da |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s100/actor/model_world_size_4_rank_3.pt | Weights | 4.4 GB | b3664372a28c |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s100/actor/optim_world_size_4_rank_0.pt | Weights | 8.0 GB | c2257d100671 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s100/actor/optim_world_size_4_rank_1.pt | Weights | 8.0 GB | 5ea5d1d58fb9 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s100/actor/optim_world_size_4_rank_2.pt | Weights | 8.0 GB | e98b6b5f34e4 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s100/actor/optim_world_size_4_rank_3.pt | Weights | 8.0 GB | f0cf7298211b |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s100/data.pt | Weights | 1.9 KB | ac34721b7b43 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s30/actor/extra_state_world_size_4_rank_0.pt | Weights | 15.1 KB | e083aca7e46f |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s30/actor/extra_state_world_size_4_rank_1.pt | Weights | 15.1 KB | 8df53b08e0f4 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s30/actor/extra_state_world_size_4_rank_2.pt | Weights | 15.1 KB | b619e1415c7f |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s30/actor/extra_state_world_size_4_rank_3.pt | Weights | 15.1 KB | cc9f1af2c732 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s30/actor/model_world_size_4_rank_0.pt | Weights | 4.4 GB | ed985d59f5bc |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s30/actor/model_world_size_4_rank_1.pt | Weights | 4.4 GB | ba9c6796c3a0 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s30/actor/model_world_size_4_rank_2.pt | Weights | 4.4 GB | 9836a96c581f |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s30/actor/model_world_size_4_rank_3.pt | Weights | 4.4 GB | eb9ccb9d129e |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s30/actor/optim_world_size_4_rank_0.pt | Weights | 8.0 GB | 158634260137 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s30/actor/optim_world_size_4_rank_1.pt | Weights | 8.0 GB | 37f774949240 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s30/actor/optim_world_size_4_rank_2.pt | Weights | 8.0 GB | e23054486d15 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s30/actor/optim_world_size_4_rank_3.pt | Weights | 8.0 GB | 4ea0811b31b1 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s30/data.pt | Weights | 1.9 KB | 371d6a4186b6 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s55/actor/extra_state_world_size_4_rank_0.pt | Weights | 15.1 KB | 5d7ea286a0eb |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s55/actor/extra_state_world_size_4_rank_1.pt | Weights | 15.1 KB | fe66d3fd9a03 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s55/actor/extra_state_world_size_4_rank_2.pt | Weights | 15.1 KB | 6fa509f28a23 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s55/actor/extra_state_world_size_4_rank_3.pt | Weights | 15.1 KB | 740437368408 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s55/actor/model_world_size_4_rank_0.pt | Weights | 4.4 GB | 96f01f54d932 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s55/actor/model_world_size_4_rank_1.pt | Weights | 4.4 GB | f608f1a6ed36 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s55/actor/model_world_size_4_rank_2.pt | Weights | 4.4 GB | 3a97bd61710e |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s55/actor/model_world_size_4_rank_3.pt | Weights | 4.4 GB | a57ae73cfd18 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s55/actor/optim_world_size_4_rank_0.pt | Weights | 8.0 GB | f0f6868ecba7 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s55/actor/optim_world_size_4_rank_1.pt | Weights | 8.0 GB | fbe23f68d8ce |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s55/actor/optim_world_size_4_rank_2.pt | Weights | 8.0 GB | bbc02addcf60 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s55/actor/optim_world_size_4_rank_3.pt | Weights | 8.0 GB | 8b420f68fe7d |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s55/data.pt | Weights | 1.9 KB | 98abfd1c7094 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s85/actor/extra_state_world_size_4_rank_0.pt | Weights | 15.1 KB | 4b4d86f39a87 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s85/actor/extra_state_world_size_4_rank_1.pt | Weights | 15.1 KB | cfdbbbeee4c9 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s85/actor/extra_state_world_size_4_rank_2.pt | Weights | 15.1 KB | 70ac9a9414d7 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s85/actor/extra_state_world_size_4_rank_3.pt | Weights | 15.1 KB | 4c7cb2f6c5a3 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s85/actor/model_world_size_4_rank_0.pt | Weights | 4.4 GB | 7bdcece8a615 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s85/actor/model_world_size_4_rank_1.pt | Weights | 4.4 GB | 59ebd1cb08df |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s85/actor/model_world_size_4_rank_2.pt | Weights | 4.4 GB | f4106385a39b |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s85/actor/model_world_size_4_rank_3.pt | Weights | 4.4 GB | 7eeac6cc2d19 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s85/actor/optim_world_size_4_rank_0.pt | Weights | 8.0 GB | f7cfb7fa9942 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s85/actor/optim_world_size_4_rank_1.pt | Weights | 8.0 GB | a5ef776d1dd4 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s85/actor/optim_world_size_4_rank_2.pt | Weights | 8.0 GB | 640d8df970e4 |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s85/actor/optim_world_size_4_rank_3.pt | Weights | 8.0 GB | fdf5e2e8193d |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s85/data.pt | Weights | 1.9 KB | 954396f5c0e5 |
| grpo_qwen3-4b_ours_appworld_flash/best/model-00001-of-00002.safetensors | Weights | 5.0 GB | d5fb0453db0b |
| grpo_qwen3-4b_ours_appworld_flash/best/model-00002-of-00002.safetensors | Weights | 3.8 GB | f43d6daef066 |
| grpo_qwen3-4b_ours_appworld_flash/latest/model-00001-of-00002.safetensors | Weights | 5.0 GB | 34da37116cc0 |
| grpo_qwen3-4b_ours_appworld_flash/latest/model-00002-of-00002.safetensors | Weights | 3.8 GB | abecb78d4025 |
| grpo_qwen3-4b_ours_appworld_flash__2gpu_run_s25/anchor_s15/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 68abd8363fd6 |
| grpo_qwen3-4b_ours_appworld_flash__2gpu_run_s25/anchor_s15/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | bb004dd9cc70 |
| grpo_qwen3-4b_ours_appworld_flash__2gpu_run_s25/anchor_s15/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | 8863ea601c3c |
| grpo_qwen3-4b_ours_appworld_flash__2gpu_run_s25/anchor_s15/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | 92cbd55ee647 |
| grpo_qwen3-4b_ours_appworld_flash__2gpu_run_s25/anchor_s15/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | af38269ce92f |
| grpo_qwen3-4b_ours_appworld_flash__2gpu_run_s25/anchor_s15/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 7954fc1b423d |
| grpo_qwen3-4b_ours_appworld_flash__2gpu_run_s25/anchor_s15/data.pt | Weights | 1.9 KB | 9493dc397ff2 |
| grpo_qwen3-4b_ours_appworld_flash__2gpu_run_s25/anchor_s25/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | d7fbcbdc387b |
| grpo_qwen3-4b_ours_appworld_flash__2gpu_run_s25/anchor_s25/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | 22b4d5324c51 |
| grpo_qwen3-4b_ours_appworld_flash__2gpu_run_s25/anchor_s25/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | 5c73fef90fdd |
| grpo_qwen3-4b_ours_appworld_flash__2gpu_run_s25/anchor_s25/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | 43f9d3662f89 |
| grpo_qwen3-4b_ours_appworld_flash__2gpu_run_s25/anchor_s25/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | 2393f4177f24 |
| grpo_qwen3-4b_ours_appworld_flash__2gpu_run_s25/anchor_s25/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 9e414f550995 |
| grpo_qwen3-4b_ours_appworld_flash__2gpu_run_s25/anchor_s25/data.pt | Weights | 1.9 KB | e4b9f998899a |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s30/actor/extra_state_world_size_4_rank_0.pt | Weights | 15.1 KB | e083aca7e46f |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s30/actor/extra_state_world_size_4_rank_1.pt | Weights | 15.1 KB | 8df53b08e0f4 |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s30/actor/extra_state_world_size_4_rank_2.pt | Weights | 15.1 KB | b619e1415c7f |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s30/actor/extra_state_world_size_4_rank_3.pt | Weights | 15.1 KB | cc9f1af2c732 |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s30/actor/model_world_size_4_rank_0.pt | Weights | 4.4 GB | da0c13bca9c7 |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s30/actor/model_world_size_4_rank_1.pt | Weights | 4.4 GB | b9989b43b7e4 |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s30/actor/model_world_size_4_rank_2.pt | Weights | 4.4 GB | 2d4bd341362c |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s30/actor/model_world_size_4_rank_3.pt | Weights | 4.4 GB | 911e64ed16e2 |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s30/actor/optim_world_size_4_rank_0.pt | Weights | 8.0 GB | 98b280ca7263 |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s30/actor/optim_world_size_4_rank_1.pt | Weights | 8.0 GB | 951fb9078733 |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s30/actor/optim_world_size_4_rank_2.pt | Weights | 8.0 GB | c840def9bbc6 |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s30/actor/optim_world_size_4_rank_3.pt | Weights | 8.0 GB | 9cf3467e0191 |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s30/data.pt | Weights | 1.9 KB | fe355a386a81 |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s95/actor/extra_state_world_size_4_rank_0.pt | Weights | 15.1 KB | d9c6f4c8f975 |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s95/actor/extra_state_world_size_4_rank_1.pt | Weights | 15.1 KB | 5d518c0d4d4b |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s95/actor/extra_state_world_size_4_rank_2.pt | Weights | 15.1 KB | 190696937c0a |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s95/actor/extra_state_world_size_4_rank_3.pt | Weights | 15.1 KB | cc8618e4904b |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s95/actor/model_world_size_4_rank_0.pt | Weights | 4.4 GB | 49c65b1f18c4 |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s95/actor/model_world_size_4_rank_1.pt | Weights | 4.4 GB | 58c866b5cfea |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s95/actor/model_world_size_4_rank_2.pt | Weights | 4.4 GB | 326303c79ea7 |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s95/actor/model_world_size_4_rank_3.pt | Weights | 4.4 GB | 06932e600409 |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s95/actor/optim_world_size_4_rank_0.pt | Weights | 8.0 GB | 3faa18c30002 |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s95/actor/optim_world_size_4_rank_1.pt | Weights | 8.0 GB | 4303dc080795 |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s95/actor/optim_world_size_4_rank_2.pt | Weights | 8.0 GB | c8ad6d9b1eaf |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s95/actor/optim_world_size_4_rank_3.pt | Weights | 8.0 GB | 34eec3af2073 |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s95/data.pt | Weights | 1.9 KB | 7053ed884dc7 |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s99/actor/extra_state_world_size_4_rank_0.pt | Weights | 15.1 KB | a9104325878b |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s99/actor/extra_state_world_size_4_rank_1.pt | Weights | 15.1 KB | 3a5bbe09c8ad |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s99/actor/extra_state_world_size_4_rank_2.pt | Weights | 15.1 KB | edf681fc6e48 |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s99/actor/extra_state_world_size_4_rank_3.pt | Weights | 15.1 KB | 1344c17813a5 |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s99/actor/model_world_size_4_rank_0.pt | Weights | 4.4 GB | ea82fc983083 |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s99/actor/model_world_size_4_rank_1.pt | Weights | 4.4 GB | 1be57a3782ce |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s99/actor/model_world_size_4_rank_2.pt | Weights | 4.4 GB | dae461e83e46 |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s99/actor/model_world_size_4_rank_3.pt | Weights | 4.4 GB | 04131f4e0b28 |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s99/actor/optim_world_size_4_rank_0.pt | Weights | 8.0 GB | 4bc880896b5b |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s99/actor/optim_world_size_4_rank_1.pt | Weights | 8.0 GB | c7557f08153e |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s99/actor/optim_world_size_4_rank_2.pt | Weights | 8.0 GB | ab4fa9176b1e |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s99/actor/optim_world_size_4_rank_3.pt | Weights | 8.0 GB | 764bd24cc9d4 |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s99/data.pt | Weights | 1.9 KB | f4e0752b697d |
| grpo_qwen3-4b_ours_appworld_luna/best/model-00001-of-00002.safetensors | Weights | 5.0 GB | 5700b02548b9 |
| grpo_qwen3-4b_ours_appworld_luna/best/model-00002-of-00002.safetensors | Weights | 3.9 GB | 4dfef2fd0f97 |
| grpo_qwen3-4b_ours_appworld_luna/latest/model-00001-of-00002.safetensors | Weights | 5.0 GB | 86a0d0a418f3 |
| grpo_qwen3-4b_ours_appworld_luna/latest/model-00002-of-00002.safetensors | Weights | 3.9 GB | ccce9ac88b77 |
| grpo_qwen3-4b_ours_appworld_luna/rescued_s60/model-00001-of-00002.safetensors | Weights | 5.0 GB | 5700b02548b9 |
| grpo_qwen3-4b_ours_appworld_luna/rescued_s60/model-00002-of-00002.safetensors | Weights | 3.9 GB | 4dfef2fd0f97 |
| grpo_qwen3-4b_ours_appworld_luna__2gpu_run_s20/anchor_s15/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 68abd8363fd6 |
| grpo_qwen3-4b_ours_appworld_luna__2gpu_run_s20/anchor_s15/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | bb004dd9cc70 |
| grpo_qwen3-4b_ours_appworld_luna__2gpu_run_s20/anchor_s15/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | d06eac53939b |
| grpo_qwen3-4b_ours_appworld_luna__2gpu_run_s20/anchor_s15/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | 95e516b7b661 |
| grpo_qwen3-4b_ours_appworld_luna__2gpu_run_s20/anchor_s15/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | f82e12d990f5 |
| grpo_qwen3-4b_ours_appworld_luna__2gpu_run_s20/anchor_s15/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | c5106da91e43 |
| grpo_qwen3-4b_ours_appworld_luna__2gpu_run_s20/anchor_s15/data.pt | Weights | 1.9 KB | ddeb0577ba99 |
| grpo_qwen3-4b_ours_appworld_luna__2gpu_run_s20/anchor_s20/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | d8bf265029d5 |
| grpo_qwen3-4b_ours_appworld_luna__2gpu_run_s20/anchor_s20/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | 574b2f1e946c |
| grpo_qwen3-4b_ours_appworld_luna__2gpu_run_s20/anchor_s20/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | af231cb453d1 |
| grpo_qwen3-4b_ours_appworld_luna__2gpu_run_s20/anchor_s20/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | 7c97fd182fe1 |
| grpo_qwen3-4b_ours_appworld_luna__2gpu_run_s20/anchor_s20/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | adbd506b2799 |
| grpo_qwen3-4b_ours_appworld_luna__2gpu_run_s20/anchor_s20/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 9ed8856fc5f8 |
| grpo_qwen3-4b_ours_appworld_luna__2gpu_run_s20/anchor_s20/data.pt | Weights | 1.9 KB | e3b29285d1b1 |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s15/actor/extra_state_world_size_4_rank_0.pt | Weights | 15.1 KB | e1350a277030 |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s15/actor/extra_state_world_size_4_rank_1.pt | Weights | 15.1 KB | 0096f686de36 |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s15/actor/extra_state_world_size_4_rank_2.pt | Weights | 15.1 KB | 4efed2239cca |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s15/actor/extra_state_world_size_4_rank_3.pt | Weights | 15.1 KB | 53f37a080efb |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s15/actor/model_world_size_4_rank_0.pt | Weights | 4.4 GB | b0205b24fe75 |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s15/actor/model_world_size_4_rank_1.pt | Weights | 4.4 GB | 0b78c50e317a |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s15/actor/model_world_size_4_rank_2.pt | Weights | 4.4 GB | 236015c1c539 |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s15/actor/model_world_size_4_rank_3.pt | Weights | 4.4 GB | 4e26fb499f75 |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s15/actor/optim_world_size_4_rank_0.pt | Weights | 8.0 GB | 1d63228c69cb |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s15/actor/optim_world_size_4_rank_1.pt | Weights | 8.0 GB | 6efc54c0ae27 |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s15/actor/optim_world_size_4_rank_2.pt | Weights | 8.0 GB | 2cf1c2ea62a5 |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s15/actor/optim_world_size_4_rank_3.pt | Weights | 8.0 GB | 99fe043a92bf |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s15/data.pt | Weights | 1.9 KB | 5f29b81f0d22 |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s17/actor/extra_state_world_size_4_rank_0.pt | Weights | 15.1 KB | 7a6b07d6eecd |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s17/actor/extra_state_world_size_4_rank_1.pt | Weights | 15.1 KB | dff47b579397 |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s17/actor/extra_state_world_size_4_rank_2.pt | Weights | 15.1 KB | 02d436820da0 |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s17/actor/extra_state_world_size_4_rank_3.pt | Weights | 15.1 KB | 128e74e47f24 |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s17/actor/model_world_size_4_rank_0.pt | Weights | 4.4 GB | d28152d3e996 |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s17/actor/model_world_size_4_rank_1.pt | Weights | 4.4 GB | 460544f49ae6 |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s17/actor/model_world_size_4_rank_2.pt | Weights | 4.4 GB | ac5b962dbe5c |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s17/actor/model_world_size_4_rank_3.pt | Weights | 4.4 GB | b832a8862cbe |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s17/actor/optim_world_size_4_rank_0.pt | Weights | 8.0 GB | 5e2862ec1c29 |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s17/actor/optim_world_size_4_rank_1.pt | Weights | 8.0 GB | 789a93da2768 |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s17/actor/optim_world_size_4_rank_2.pt | Weights | 8.0 GB | 567b57e7b6f3 |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s17/actor/optim_world_size_4_rank_3.pt | Weights | 8.0 GB | 181fe4fb1e8d |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s17/data.pt | Weights | 1.9 KB | f68795cdeae1 |
| grpo_qwen3-4b_ours_appworld_luna_sft/best/model-00001-of-00002.safetensors | Weights | 5.0 GB | 6a0db4ab8d46 |
| grpo_qwen3-4b_ours_appworld_luna_sft/best/model-00002-of-00002.safetensors | Weights | 3.8 GB | f595a8fca592 |
| grpo_qwen3-4b_ours_appworld_luna_sft/best_s5/model-00001-of-00002.safetensors | Weights | 5.0 GB | 6a0db4ab8d46 |
| grpo_qwen3-4b_ours_appworld_luna_sft/best_s5/model-00002-of-00002.safetensors | Weights | 3.8 GB | f595a8fca592 |
| grpo_qwen3-4b_ours_appworld_luna_sft/latest/model-00001-of-00002.safetensors | Weights | 5.0 GB | 0da02ace32c4 |
| grpo_qwen3-4b_ours_appworld_luna_sft/latest/model-00002-of-00002.safetensors | Weights | 3.8 GB | fc00391ce7ed |
| grpo_qwen3-4b_ours_appworld_luna_sft__4gpu_run_s4/anchor_s4/actor/extra_state_world_size_4_rank_0.pt | Weights | 15.1 KB | 2bc6487255ad |
| grpo_qwen3-4b_ours_appworld_luna_sft__4gpu_run_s4/anchor_s4/actor/extra_state_world_size_4_rank_1.pt | Weights | 15.1 KB | 0ead6d3c4517 |
| grpo_qwen3-4b_ours_appworld_luna_sft__4gpu_run_s4/anchor_s4/actor/extra_state_world_size_4_rank_2.pt | Weights | 15.1 KB | 04a544b089e1 |
| grpo_qwen3-4b_ours_appworld_luna_sft__4gpu_run_s4/anchor_s4/actor/extra_state_world_size_4_rank_3.pt | Weights | 15.1 KB | ec6003765e42 |
| grpo_qwen3-4b_ours_appworld_luna_sft__4gpu_run_s4/anchor_s4/actor/model_world_size_4_rank_0.pt | Weights | 4.4 GB | dc78dd17dd54 |
| grpo_qwen3-4b_ours_appworld_luna_sft__4gpu_run_s4/anchor_s4/actor/model_world_size_4_rank_1.pt | Weights | 4.4 GB | 62f29e9310d7 |
| grpo_qwen3-4b_ours_appworld_luna_sft__4gpu_run_s4/anchor_s4/actor/model_world_size_4_rank_2.pt | Weights | 4.4 GB | 221b0f0c748a |
| grpo_qwen3-4b_ours_appworld_luna_sft__4gpu_run_s4/anchor_s4/actor/model_world_size_4_rank_3.pt | Weights | 4.4 GB | 27c41d3d13f8 |
| grpo_qwen3-4b_ours_appworld_luna_sft__4gpu_run_s4/anchor_s4/actor/optim_world_size_4_rank_0.pt | Weights | 8.0 GB | 49e83c39c4bd |
| grpo_qwen3-4b_ours_appworld_luna_sft__4gpu_run_s4/anchor_s4/actor/optim_world_size_4_rank_1.pt | Weights | 8.0 GB | 25fe41509eee |
| grpo_qwen3-4b_ours_appworld_luna_sft__4gpu_run_s4/anchor_s4/actor/optim_world_size_4_rank_2.pt | Weights | 8.0 GB | 723bd033c193 |
| grpo_qwen3-4b_ours_appworld_luna_sft__4gpu_run_s4/anchor_s4/actor/optim_world_size_4_rank_3.pt | Weights | 8.0 GB | f3028fd4cf43 |
| grpo_qwen3-4b_ours_appworld_luna_sft__4gpu_run_s4/anchor_s4/data.pt | Weights | 1.9 KB | d5b319dc42c7 |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/actor/extra_state_world_size_8_rank_0.pt | Weights | 15.1 KB | cf1233d9865b |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/actor/extra_state_world_size_8_rank_1.pt | Weights | 15.1 KB | d1235c22482a |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/actor/extra_state_world_size_8_rank_2.pt | Weights | 15.1 KB | 5b3ff3ecb305 |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/actor/extra_state_world_size_8_rank_3.pt | Weights | 15.1 KB | 8b17d1fdc3bb |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/actor/extra_state_world_size_8_rank_4.pt | Weights | 15.1 KB | cf136dadfe26 |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/actor/extra_state_world_size_8_rank_5.pt | Weights | 15.1 KB | b3f0a8fe8460 |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/actor/extra_state_world_size_8_rank_6.pt | Weights | 15.1 KB | d08227b9277c |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/actor/extra_state_world_size_8_rank_7.pt | Weights | 15.1 KB | 74ba22809a68 |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/actor/model_world_size_8_rank_0.pt | Weights | 2.2 GB | 0954ca6ed5e1 |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/actor/model_world_size_8_rank_1.pt | Weights | 2.2 GB | 199e3af30468 |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/actor/model_world_size_8_rank_2.pt | Weights | 2.2 GB | 9f74e3b90c3a |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/actor/model_world_size_8_rank_3.pt | Weights | 2.2 GB | 71eab757bc2e |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/actor/model_world_size_8_rank_4.pt | Weights | 2.2 GB | fadb92f97d1a |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/actor/model_world_size_8_rank_5.pt | Weights | 2.2 GB | a2a272331a18 |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/actor/model_world_size_8_rank_6.pt | Weights | 2.2 GB | d2da5343ad23 |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/actor/model_world_size_8_rank_7.pt | Weights | 2.2 GB | 046293ff9cdb |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/actor/optim_world_size_8_rank_0.pt | Weights | 4.0 GB | defd1668b3a1 |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/actor/optim_world_size_8_rank_1.pt | Weights | 4.0 GB | 3f19b142202f |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/actor/optim_world_size_8_rank_2.pt | Weights | 4.0 GB | 38c60e85a0e7 |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/actor/optim_world_size_8_rank_3.pt | Weights | 4.0 GB | f5ae56d9d60f |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/actor/optim_world_size_8_rank_4.pt | Weights | 4.0 GB | d99d1197cc81 |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/actor/optim_world_size_8_rank_5.pt | Weights | 4.0 GB | 1897f6f31a3a |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/actor/optim_world_size_8_rank_6.pt | Weights | 4.0 GB | a7ee43d500ee |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/actor/optim_world_size_8_rank_7.pt | Weights | 4.0 GB | af495280ab83 |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/data.pt | Weights | 1.9 KB | 4340c21d7148 |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/actor/extra_state_world_size_8_rank_0.pt | Weights | 15.1 KB | 221f2a45e19f |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/actor/extra_state_world_size_8_rank_1.pt | Weights | 15.1 KB | 508ea865989c |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/actor/extra_state_world_size_8_rank_2.pt | Weights | 15.1 KB | 0608084d7da9 |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/actor/extra_state_world_size_8_rank_3.pt | Weights | 15.1 KB | 827f2f260af0 |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/actor/extra_state_world_size_8_rank_4.pt | Weights | 15.1 KB | 6617841c908d |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/actor/extra_state_world_size_8_rank_5.pt | Weights | 15.1 KB | 94eab039ff4e |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/actor/extra_state_world_size_8_rank_6.pt | Weights | 15.1 KB | 6a5249055b06 |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/actor/extra_state_world_size_8_rank_7.pt | Weights | 15.1 KB | 73d7011305dd |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/actor/model_world_size_8_rank_0.pt | Weights | 2.2 GB | f9a2135afb22 |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/actor/model_world_size_8_rank_1.pt | Weights | 2.2 GB | 5934c8755f7d |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/actor/model_world_size_8_rank_2.pt | Weights | 2.2 GB | 4f015ac3abf1 |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/actor/model_world_size_8_rank_3.pt | Weights | 2.2 GB | 2d5a44db1cb5 |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/actor/model_world_size_8_rank_4.pt | Weights | 2.2 GB | f526628af477 |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/actor/model_world_size_8_rank_5.pt | Weights | 2.2 GB | 0dcabcb8118e |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/actor/model_world_size_8_rank_6.pt | Weights | 2.2 GB | 10aa4064a8e9 |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/actor/model_world_size_8_rank_7.pt | Weights | 2.2 GB | ce8a69bec390 |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/actor/optim_world_size_8_rank_0.pt | Weights | 4.0 GB | 21d90f19b3e7 |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/actor/optim_world_size_8_rank_1.pt | Weights | 4.0 GB | 239ace53ec77 |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/actor/optim_world_size_8_rank_2.pt | Weights | 4.0 GB | 5a1e5934e335 |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/actor/optim_world_size_8_rank_3.pt | Weights | 4.0 GB | c2377ee3f4b3 |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/actor/optim_world_size_8_rank_4.pt | Weights | 4.0 GB | f3391ff1a32d |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/actor/optim_world_size_8_rank_5.pt | Weights | 4.0 GB | e0ae6f6093d2 |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/actor/optim_world_size_8_rank_6.pt | Weights | 4.0 GB | 0972047b92a1 |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/actor/optim_world_size_8_rank_7.pt | Weights | 4.0 GB | f04d5d9dbceb |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/data.pt | Weights | 1.9 KB | 94b46f823b26 |
| grpo_qwen3-4b_skillrl_alf_flash/anchor_s121/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 6746fa0a8760 |
| grpo_qwen3-4b_skillrl_alf_flash/anchor_s121/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | c4eff83a3852 |
| grpo_qwen3-4b_skillrl_alf_flash/anchor_s121/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | 65c73933facc |
| grpo_qwen3-4b_skillrl_alf_flash/anchor_s121/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | 104b5d9c29a2 |
| grpo_qwen3-4b_skillrl_alf_flash/anchor_s121/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | 0ba0cd5674ac |
| grpo_qwen3-4b_skillrl_alf_flash/anchor_s121/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 8c5f1906ccf5 |
| grpo_qwen3-4b_skillrl_alf_flash/anchor_s121/data.pt | Weights | 1.9 KB | 3c40d0d37d51 |
| grpo_qwen3-4b_skillrl_alf_flash/anchor_s40/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 0a61cd794f63 |
| grpo_qwen3-4b_skillrl_alf_flash/anchor_s40/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | 228decfdab68 |
| grpo_qwen3-4b_skillrl_alf_flash/anchor_s40/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | a6cc2e947435 |
| grpo_qwen3-4b_skillrl_alf_flash/anchor_s40/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | 8efe4bcb0e49 |
| grpo_qwen3-4b_skillrl_alf_flash/anchor_s40/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | dfc7e8748908 |
| grpo_qwen3-4b_skillrl_alf_flash/anchor_s40/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | ef87ef55e546 |
| grpo_qwen3-4b_skillrl_alf_flash/anchor_s40/data.pt | Weights | 1.9 KB | 3bc5829bca23 |
| grpo_qwen3-4b_skillrl_alf_flash/best/model-00001-of-00002.safetensors | Weights | 5.0 GB | ac98e17daaed |
| grpo_qwen3-4b_skillrl_alf_flash/best/model-00002-of-00002.safetensors | Weights | 3.8 GB | 25d75b7d3554 |
| grpo_qwen3-4b_skillrl_alf_flash/latest/model-00001-of-00002.safetensors | Weights | 5.0 GB | ebe7fac508c5 |
| grpo_qwen3-4b_skillrl_alf_flash/latest/model-00002-of-00002.safetensors | Weights | 3.9 GB | 9068a1a86782 |
| grpo_qwen3-4b_skillrl_alf_flash/rescued_s75/model-00001-of-00002.safetensors | Weights | 5.0 GB | ac98e17daaed |
| grpo_qwen3-4b_skillrl_alf_flash/rescued_s75/model-00002-of-00002.safetensors | Weights | 3.8 GB | 25d75b7d3554 |
| grpo_qwen3-4b_v6_2/anchor_s160/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 78d1a1ff7bec |
| grpo_qwen3-4b_v6_2/anchor_s160/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | d22b882a0d6b |
| grpo_qwen3-4b_v6_2/anchor_s160/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | 4cd4ec7fd29c |
| grpo_qwen3-4b_v6_2/anchor_s160/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | 84b35f80ece6 |
| grpo_qwen3-4b_v6_2/anchor_s160/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | b3e27f1f0043 |
| grpo_qwen3-4b_v6_2/anchor_s160/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 72662ce82b5a |
| grpo_qwen3-4b_v6_2/anchor_s160/data.pt | Weights | 1.9 KB | badf9e51ba08 |
| grpo_qwen3-4b_v6_2/anchor_s190/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 6d765e61565d |
| grpo_qwen3-4b_v6_2/anchor_s190/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | 642c3bb02a02 |
| grpo_qwen3-4b_v6_2/anchor_s190/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | b2eda90b3a17 |
| grpo_qwen3-4b_v6_2/anchor_s190/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | bd927b0f7228 |
| grpo_qwen3-4b_v6_2/anchor_s190/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | 60447cdc9f2c |
| grpo_qwen3-4b_v6_2/anchor_s190/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | e21f6618e9b9 |
| grpo_qwen3-4b_v6_2/anchor_s190/data.pt | Weights | 1.9 KB | 11b0547f7863 |
| grpo_qwen3-4b_v6_2/best/model-00001-of-00002.safetensors | Weights | 5.0 GB | 59939fd0f7c5 |
| grpo_qwen3-4b_v6_2/best/model-00002-of-00002.safetensors | Weights | 3.9 GB | 17ef4f7d62ab |
| grpo_qwen3-4b_v6_2/latest/model-00001-of-00002.safetensors | Weights | 4.5 GB | 65713df5bc4b |
| grpo_qwen3-4b_v6_2/latest/model-00002-of-00002.safetensors | Weights | 4.3 GB | b4bd66dc625b |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s123/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | d5a3d9fb7e5c |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s123/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | 47d298906178 |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s123/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | 7e4ffad0ce62 |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s123/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | ba1d9de096de |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s123/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | 9e39367154f3 |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s123/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 5d84cce48110 |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s123/data.pt | Weights | 1.9 KB | 150cc7354fc4 |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s160/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 78d1a1ff7bec |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s160/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | d22b882a0d6b |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s160/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | b61dfffd1ea9 |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s160/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | a04f01345a26 |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s160/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | d95ba804b8a3 |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s160/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 9fa6c105e1a0 |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s160/data.pt | Weights | 1.9 KB | 73ae4c5e49ab |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s40/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 0a61cd794f63 |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s40/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | 228decfdab68 |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s40/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | 82716c759e76 |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s40/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | bb83eedaa6fc |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s40/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | db700ac3bbfb |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s40/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | a3be2009e93b |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s40/data.pt | Weights | 1.9 KB | c1fa68194412 |
| grpo_qwen3-4b_v6_2_ablA1_bundle/best/model-00001-of-00002.safetensors | Weights | 4.5 GB | e88c87826bc1 |
| grpo_qwen3-4b_v6_2_ablA1_bundle/best/model-00002-of-00002.safetensors | Weights | 4.3 GB | 54c9ad0c575d |
| grpo_qwen3-4b_v6_2_ablA1_bundle/best_s60/model-00001-of-00002.safetensors | Weights | 4.5 GB | e88c87826bc1 |
| grpo_qwen3-4b_v6_2_ablA1_bundle/best_s60/model-00002-of-00002.safetensors | Weights | 4.3 GB | 54c9ad0c575d |
| grpo_qwen3-4b_v6_2_ablA1_bundle/latest/model-00001-of-00002.safetensors | Weights | 5.0 GB | cc4a57bf1efa |
| grpo_qwen3-4b_v6_2_ablA1_bundle/latest/model-00002-of-00002.safetensors | Weights | 3.8 GB | 29309794ca80 |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s130/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 52bf4b56ab56 |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s130/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | 32a5649228cf |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s130/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | 3d6c97daa58c |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s130/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | c60d07ceaf02 |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s130/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | 9c92c2eec4e1 |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s130/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 528a93118885 |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s130/data.pt | Weights | 1.9 KB | 232cbb5f0f49 |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s159/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 0eb9be108ae9 |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s159/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | 8885b1a8a77e |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s159/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | 5e9808638bc0 |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s159/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | c4302d3c4e73 |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s159/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | b5afdfe20587 |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s159/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 963dfc06fa68 |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s159/data.pt | Weights | 1.9 KB | 1d8b70b86d43 |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s160/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 78d1a1ff7bec |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s160/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | d22b882a0d6b |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s160/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | 201e59005916 |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s160/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | 050064a38c40 |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s160/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | c5826d9adc45 |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s160/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 463a6e3f1537 |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s160/data.pt | Weights | 1.9 KB | 4a7cac7ef5fe |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s40/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 0a61cd794f63 |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s40/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | 228decfdab68 |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s40/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | d116d4ee7934 |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s40/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | a77ea2d229e4 |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s40/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | 4cdc940eec77 |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s40/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | ef2f9351fbff |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s40/data.pt | Weights | 1.9 KB | cda171104f29 |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/best/model-00001-of-00002.safetensors | Weights | 5.0 GB | bf0a06303801 |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/best/model-00002-of-00002.safetensors | Weights | 3.8 GB | baa9a8d3c1f8 |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/latest/model-00001-of-00002.safetensors | Weights | 5.0 GB | 02ababa2a16c |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/latest/model-00002-of-00002.safetensors | Weights | 3.8 GB | c80fe70e076d |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/rescued_s80/model-00001-of-00002.safetensors | Weights | 5.0 GB | bf0a06303801 |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/rescued_s80/model-00002-of-00002.safetensors | Weights | 3.8 GB | baa9a8d3c1f8 |
| grpo_qwen3-4b_v6_2_r110/anchor_s160/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 78d1a1ff7bec |
| grpo_qwen3-4b_v6_2_r110/anchor_s160/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | d22b882a0d6b |
| grpo_qwen3-4b_v6_2_r110/anchor_s160/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | f1bda9c65aaa |
| grpo_qwen3-4b_v6_2_r110/anchor_s160/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | 8b0ca6671209 |
| grpo_qwen3-4b_v6_2_r110/anchor_s160/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | 09f54017b154 |
| grpo_qwen3-4b_v6_2_r110/anchor_s160/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 727daf6d54db |
| grpo_qwen3-4b_v6_2_r110/anchor_s160/data.pt | Weights | 1.9 KB | d53d7abd76ce |
| grpo_qwen3-4b_v6_2_r110/best/model-00001-of-00002.safetensors | Weights | 4.4 GB | d2262229474d |
| grpo_qwen3-4b_v6_2_r110/best/model-00002-of-00002.safetensors | Weights | 4.4 GB | 735f44a1f6b7 |
| grpo_qwen3-4b_v6_2_r110/best_s150/model-00001-of-00002.safetensors | Weights | 4.4 GB | d2262229474d |
| grpo_qwen3-4b_v6_2_r110/best_s150/model-00002-of-00002.safetensors | Weights | 4.4 GB | 735f44a1f6b7 |
| grpo_qwen3-4b_v6_2_r110/latest/model-00001-of-00002.safetensors | Weights | 5.0 GB | e71d096bb214 |
| grpo_qwen3-4b_v6_2_r110/latest/model-00002-of-00002.safetensors | Weights | 3.9 GB | 411006efbc1b |
| grpo_qwen3-4b_v6_2_sft/anchor_s190/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 6d765e61565d |
| grpo_qwen3-4b_v6_2_sft/anchor_s190/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | 642c3bb02a02 |
| grpo_qwen3-4b_v6_2_sft/anchor_s190/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | 35ceb25a2565 |
| grpo_qwen3-4b_v6_2_sft/anchor_s190/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | edfdb6a3960c |
| grpo_qwen3-4b_v6_2_sft/anchor_s190/actor/optim_world_size_2_rank_0.pt | Weights | 16.1 GB | 0705ac63f972 |
| grpo_qwen3-4b_v6_2_sft/anchor_s190/actor/optim_world_size_2_rank_1.pt | Weights | 16.1 GB | 196275f0dfc3 |
| grpo_qwen3-4b_v6_2_sft/anchor_s190/data.pt | Weights | 1.9 KB | 85e528ee2cde |
| grpo_qwen3-4b_v6_2_sft/best/model-00001-of-00002.safetensors | Weights | 5.0 GB | 19a8a0bca91d |
| grpo_qwen3-4b_v6_2_sft/best/model-00002-of-00002.safetensors | Weights | 3.8 GB | d3d07739c97a |
| grpo_qwen3-4b_v6_2_sft/latest/model-00001-of-00002.safetensors | Weights | 4.5 GB | 33e470244684 |
| grpo_qwen3-4b_v6_2_sft/latest/model-00002-of-00002.safetensors | Weights | 4.3 GB | 76f01b62df2a |
| grpo_qwen3-4b_v6_2_sft/rescued_best/anchor_s160_modelonly/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 78d1a1ff7bec |
| grpo_qwen3-4b_v6_2_sft/rescued_best/anchor_s160_modelonly/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | d22b882a0d6b |
| grpo_qwen3-4b_v6_2_sft/rescued_best/anchor_s160_modelonly/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | 03d9753a670e |
| grpo_qwen3-4b_v6_2_sft/rescued_best/anchor_s160_modelonly/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | 121a17837373 |
| grpo_qwen3-4b_v6_2_sft/rescued_best/anchor_s160_modelonly/data.pt | Weights | 1.9 KB | 740083982ee0 |
| grpo_qwen3-4b_v6_2_sft/rescued_s160/actor/extra_state_world_size_2_rank_0.pt | Weights | 15.1 KB | 78d1a1ff7bec |
| grpo_qwen3-4b_v6_2_sft/rescued_s160/actor/extra_state_world_size_2_rank_1.pt | Weights | 15.1 KB | d22b882a0d6b |
| grpo_qwen3-4b_v6_2_sft/rescued_s160/actor/model_world_size_2_rank_0.pt | Weights | 8.8 GB | 03d9753a670e |
| grpo_qwen3-4b_v6_2_sft/rescued_s160/actor/model_world_size_2_rank_1.pt | Weights | 8.8 GB | 121a17837373 |
| grpo_qwen3-4b_v6_2_sft/rescued_s160/data.pt | Weights | 1.9 KB | 740083982ee0 |
| merged/grpo_qwen3-4b_d2skill_sft/best_s80/model-00001-of-00002.safetensors | Weights | 4.7 GB | 693ad0e74297 |
| merged/grpo_qwen3-4b_d2skill_sft/best_s80/model-00002-of-00002.safetensors | Weights | 4.2 GB | 926f086e15c7 |
| merged/grpo_qwen3-4b_v6_2_sft/best_s140/model-00001-of-00002.safetensors | Weights | 4.6 GB | d1ab0a0de083 |
| merged/grpo_qwen3-4b_v6_2_sft/best_s140/model-00002-of-00002.safetensors | Weights | 4.3 GB | 26a9e9d4e7a6 |
| checkpoints/grpo_qwen3-4b_d2skill_base/global_step_10/actor/added_tokens.json | Configuration | 707 B | — |
| checkpoints/grpo_qwen3-4b_d2skill_base/global_step_10/actor/config.json | Configuration | 1.5 KB | — |
| checkpoints/grpo_qwen3-4b_d2skill_base/global_step_10/actor/generation_config.json | Configuration | 213 B | — |
| checkpoints/grpo_qwen3-4b_d2skill_base/global_step_10/actor/special_tokens_map.json | Configuration | 613 B | — |
| checkpoints/grpo_qwen3-4b_d2skill_sft/best_ckpt_step40/actor/added_tokens.json | Configuration | 707 B | — |
| checkpoints/grpo_qwen3-4b_d2skill_sft/best_ckpt_step40/actor/config.json | Configuration | 1.5 KB | — |
| checkpoints/grpo_qwen3-4b_d2skill_sft/best_ckpt_step40/actor/generation_config.json | Configuration | 187 B | — |
| checkpoints/grpo_qwen3-4b_d2skill_sft/best_ckpt_step40/actor/special_tokens_map.json | Configuration | 613 B | — |
| checkpoints/grpo_qwen3-4b_d2skill_sft/global_step_30/actor/added_tokens.json | Configuration | 707 B | — |
| checkpoints/grpo_qwen3-4b_d2skill_sft/global_step_30/actor/config.json | Configuration | 1.5 KB | — |
| checkpoints/grpo_qwen3-4b_d2skill_sft/global_step_30/actor/generation_config.json | Configuration | 187 B | — |
| checkpoints/grpo_qwen3-4b_d2skill_sft/global_step_30/actor/special_tokens_map.json | Configuration | 613 B | — |
| checkpoints/grpo_qwen3-4b_d2skill_sft/global_step_80/actor/added_tokens.json | Configuration | 707 B | — |
| checkpoints/grpo_qwen3-4b_d2skill_sft/global_step_80/actor/config.json | Configuration | 1.5 KB | — |
| checkpoints/grpo_qwen3-4b_d2skill_sft/global_step_80/actor/generation_config.json | Configuration | 187 B | — |
| checkpoints/grpo_qwen3-4b_d2skill_sft/global_step_80/actor/special_tokens_map.json | Configuration | 613 B | — |
| checkpoints/grpo_qwen3-4b_v6/global_step_160/actor/added_tokens.json | Configuration | 707 B | — |
| checkpoints/grpo_qwen3-4b_v6/global_step_160/actor/config.json | Configuration | 1.5 KB | — |
| checkpoints/grpo_qwen3-4b_v6/global_step_160/actor/generation_config.json | Configuration | 213 B | — |
| checkpoints/grpo_qwen3-4b_v6/global_step_160/actor/special_tokens_map.json | Configuration | 613 B | — |
| checkpoints/grpo_qwen3-4b_v6_2/global_step_50/actor/added_tokens.json | Configuration | 707 B | — |
| checkpoints/grpo_qwen3-4b_v6_2/global_step_50/actor/config.json | Configuration | 1.5 KB | — |
| checkpoints/grpo_qwen3-4b_v6_2/global_step_50/actor/generation_config.json | Configuration | 213 B | — |
| checkpoints/grpo_qwen3-4b_v6_2/global_step_50/actor/special_tokens_map.json | Configuration | 613 B | — |
| checkpoints/grpo_qwen3-4b_v6_2_sft/global_step_90/actor/added_tokens.json | Configuration | 707 B | — |
| checkpoints/grpo_qwen3-4b_v6_2_sft/global_step_90/actor/config.json | Configuration | 1.5 KB | — |
| checkpoints/grpo_qwen3-4b_v6_2_sft/global_step_90/actor/generation_config.json | Configuration | 187 B | — |
| checkpoints/grpo_qwen3-4b_v6_2_sft/global_step_90/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s123/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s123/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s123/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s123/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s30/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s30/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s30/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s30/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s40/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s40/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s40/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s40/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s80/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s80/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s80/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s80/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_appworld_grpo_base/best/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_appworld_grpo_base/best/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_appworld_grpo_base/best/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_appworld_grpo_base/best/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_appworld_grpo_base/best/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_appworld_grpo_base/latest/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_appworld_grpo_base/latest/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_appworld_grpo_base/latest/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_appworld_grpo_base/latest/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_appworld_grpo_base/latest/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s129/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s129/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s129/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s129/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s129/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s130/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s130/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s130/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s130/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s130/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s95/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s95/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s95/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s95/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s95/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_appworld_skillrl_flash/anchor_s30/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_appworld_skillrl_flash/anchor_s30/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_appworld_skillrl_flash/anchor_s30/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_appworld_skillrl_flash/anchor_s30/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_appworld_skillrl_flash/anchor_s90/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_appworld_skillrl_flash/anchor_s90/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_appworld_skillrl_flash/anchor_s90/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_appworld_skillrl_flash/anchor_s90/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_appworld_skillrl_flash/best/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_appworld_skillrl_flash/best/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_appworld_skillrl_flash/best/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_appworld_skillrl_flash/best/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_appworld_skillrl_flash/best/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_appworld_skillrl_flash/latest/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_appworld_skillrl_flash/latest/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_appworld_skillrl_flash/latest/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_appworld_skillrl_flash/latest/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_appworld_skillrl_flash/latest/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_appworld_skillrl_flash/rescued_s95/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_appworld_skillrl_flash/rescued_s95/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_appworld_skillrl_flash/rescued_s95/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_appworld_skillrl_flash/rescued_s95/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_appworld_skillrl_flash/rescued_s95/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna/anchor_s30/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna/anchor_s30/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna/anchor_s30/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna/anchor_s30/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna/anchor_s95/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna/anchor_s95/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna/anchor_s95/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna/anchor_s95/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna/best/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna/best/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna/best/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna/best/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna/best/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna/latest/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna/latest/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna/latest/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna/latest/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna/latest/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna/rescued_s65/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna/rescued_s65/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna/rescued_s65/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna/rescued_s65/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna/rescued_s65/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s30/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s30/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s30/actor/generation_config.json | Configuration | 187 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s30/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s90/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s90/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s90/actor/generation_config.json | Configuration | 187 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s90/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s96/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s96/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s96/actor/generation_config.json | Configuration | 187 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s96/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/best/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/best/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/best/generation_config.json | Configuration | 187 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/best/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/best/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/latest/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/latest/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/latest/generation_config.json | Configuration | 187 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/latest/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/latest/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft_2gpu_run_s5/anchor_s5/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft_2gpu_run_s5/anchor_s5/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft_2gpu_run_s5/anchor_s5/actor/generation_config.json | Configuration | 187 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft_2gpu_run_s5/anchor_s5/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s30/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s30/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s30/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s30/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s30/bank_step30.json | Configuration | 1.1 MB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s68/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s68/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s68/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s68/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s68/bank_step68.json | Configuration | 1.7 MB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s80/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s80/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s80/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s80/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s80/bank_step80.json | Configuration | 1.7 MB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/best/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_d2skill_appworld_flash/best/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/best/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_d2skill_appworld_flash/best/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/best/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_d2skill_appworld_flash/latest/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_d2skill_appworld_flash/latest/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/latest/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_d2skill_appworld_flash/latest/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/latest/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_d2skill_appworld_flash/rescued_s50/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_d2skill_appworld_flash/rescued_s50/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/rescued_s50/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_d2skill_appworld_flash/rescued_s50/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/rescued_s50/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_d2skill_appworld_flash/rescued_s72/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_d2skill_appworld_flash/rescued_s72/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/rescued_s72/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_d2skill_appworld_flash/rescued_s72/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/rescued_s72/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s30/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s30/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s30/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s30/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s30/bank_step30.json | Configuration | 752.6 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s80/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s80/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s80/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s80/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s80/bank_step80.json | Configuration | 1.1 MB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s85/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s85/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s85/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s85/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s85/bank_step85.json | Configuration | 1.1 MB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s89/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s89/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s89/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s89/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s89/bank_step89.json | Configuration | 1.1 MB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/best/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna/best/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/best/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna/best/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/best/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna/best_s70/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna/best_s70/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/best_s70/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna/best_s70/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/best_s70/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna/latest/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna/latest/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/latest/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna/latest/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/latest/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/actor/generation_config.json | Configuration | 187 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/bank_step32.json | Configuration | 280.3 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/best/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/best/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/best/generation_config.json | Configuration | 187 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/best/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/best/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/latest/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/latest/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/latest/generation_config.json | Configuration | 187 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/latest/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/latest/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/rescued_s23/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/rescued_s23/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/rescued_s23/generation_config.json | Configuration | 187 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/rescued_s23/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/rescued_s23/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__2gpu_run_s5/anchor_s5/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__2gpu_run_s5/anchor_s5/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__2gpu_run_s5/anchor_s5/actor/generation_config.json | Configuration | 187 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__2gpu_run_s5/anchor_s5/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__2gpu_run_s5/anchor_s5/bank_step5.json | Configuration | 23.1 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__4gpu_run_s5/anchor_s5/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__4gpu_run_s5/anchor_s5/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__4gpu_run_s5/anchor_s5/actor/generation_config.json | Configuration | 187 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__4gpu_run_s5/anchor_s5/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__4gpu_run_s5/anchor_s5/bank_step5.json | Configuration | 62.8 KB | — |
| grpo_qwen3-4b_d2skill_base/anchor_s120/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_d2skill_base/anchor_s120/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_d2skill_base/anchor_s120/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_d2skill_base/anchor_s120/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_d2skill_base/anchor_s120/bank_step120.json | Configuration | 530.4 KB | — |
| grpo_qwen3-4b_d2skill_base/anchor_s160/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_d2skill_base/anchor_s160/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_d2skill_base/anchor_s160/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_d2skill_base/anchor_s160/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_d2skill_base/anchor_s160/bank_step160.json | Configuration | 555.3 KB | — |
| grpo_qwen3-4b_d2skill_base/best/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_d2skill_base/best/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_d2skill_base/best/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_d2skill_base/best/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_d2skill_base/best/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_d2skill_base/latest/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_d2skill_base/latest/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_d2skill_base/latest/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_d2skill_base/latest/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_d2skill_base/latest/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_d2skill_base/rescued_s135/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_d2skill_base/rescued_s135/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_d2skill_base/rescued_s135/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_d2skill_base/rescued_s135/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_d2skill_base/rescued_s160/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_d2skill_base/rescued_s160/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_d2skill_base/rescued_s160/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_d2skill_base/rescued_s160/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_d2skill_base/rescued_s85/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_d2skill_base/rescued_s85/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_d2skill_base/rescued_s85/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_d2skill_base/rescued_s85/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_d2skill_sft/best/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_d2skill_sft/best/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_d2skill_sft/best/generation_config.json | Configuration | 187 B | — |
| grpo_qwen3-4b_d2skill_sft/best/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_d2skill_sft/best/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s155/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s155/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s155/actor/generation_config.json | Configuration | 187 B | — |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s155/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s155/bank_step155.json | Configuration | 248.8 KB | — |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s160/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s160/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s160/actor/generation_config.json | Configuration | 187 B | — |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s160/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s160/bank_step160.json | Configuration | 253.1 KB | — |
| grpo_qwen3-4b_d2skill_sft_b80/best/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_d2skill_sft_b80/best/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_d2skill_sft_b80/best/generation_config.json | Configuration | 187 B | — |
| grpo_qwen3-4b_d2skill_sft_b80/best/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_d2skill_sft_b80/best/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_d2skill_sft_b80/latest/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_d2skill_sft_b80/latest/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_d2skill_sft_b80/latest/generation_config.json | Configuration | 187 B | — |
| grpo_qwen3-4b_d2skill_sft_b80/latest/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_d2skill_sft_b80/latest/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_gem_d2skill/anchor_s155/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_gem_d2skill/anchor_s155/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_gem_d2skill/anchor_s155/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_gem_d2skill/anchor_s155/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_gem_d2skill/anchor_s155/bank_step155.json | Configuration | 595.3 KB | — |
| grpo_qwen3-4b_gem_d2skill/anchor_s160/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_gem_d2skill/anchor_s160/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_gem_d2skill/anchor_s160/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_gem_d2skill/anchor_s160/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_gem_d2skill/anchor_s160/bank_step160.json | Configuration | 611.3 KB | — |
| grpo_qwen3-4b_gem_d2skill/best/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_gem_d2skill/best/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_gem_d2skill/best/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_gem_d2skill/best/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_gem_d2skill/best/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_gem_d2skill/latest/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_gem_d2skill/latest/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_gem_d2skill/latest/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_gem_d2skill/latest/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_gem_d2skill/latest/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_gem_d2skill/rescued_s130/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_gem_d2skill/rescued_s130/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_gem_d2skill/rescued_s130/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_gem_d2skill/rescued_s130/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_gem_v6_2/anchor_s160/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_gem_v6_2/anchor_s160/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_gem_v6_2/anchor_s160/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_gem_v6_2/anchor_s160/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_gem_v6_2/anchor_s170/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_gem_v6_2/anchor_s170/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_gem_v6_2/anchor_s170/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_gem_v6_2/anchor_s170/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_gem_v6_2/anchor_s40/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_gem_v6_2/anchor_s40/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_gem_v6_2/anchor_s40/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_gem_v6_2/anchor_s40/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_gem_v6_2/best/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_gem_v6_2/best/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_gem_v6_2/best/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_gem_v6_2/best/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_gem_v6_2/best/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_gem_v6_2/latest/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_gem_v6_2/latest/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_gem_v6_2/latest/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_gem_v6_2/latest/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_gem_v6_2/latest/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_gem_v6_2/rescued_s120/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_gem_v6_2/rescued_s120/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_gem_v6_2/rescued_s120/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_gem_v6_2/rescued_s120/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s100/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s100/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s100/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s100/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s100/bank_step100.json | Configuration | 2.2 MB | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s30/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s30/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s30/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s30/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s30/bank_step30.json | Configuration | 769.2 KB | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s55/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s55/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s55/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s55/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s55/bank_step55.json | Configuration | 1.2 MB | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s85/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s85/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s85/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s85/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s85/bank_step85.json | Configuration | 1.9 MB | — |
| grpo_qwen3-4b_ours_appworld_flash/best/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_ours_appworld_flash/best/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_ours_appworld_flash/best/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_ours_appworld_flash/best/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_ours_appworld_flash/best/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_ours_appworld_flash/latest/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_ours_appworld_flash/latest/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_ours_appworld_flash/latest/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_ours_appworld_flash/latest/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_ours_appworld_flash/latest/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_ours_appworld_flash__2gpu_run_s25/anchor_s15/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_ours_appworld_flash__2gpu_run_s25/anchor_s15/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_ours_appworld_flash__2gpu_run_s25/anchor_s15/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_ours_appworld_flash__2gpu_run_s25/anchor_s15/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_ours_appworld_flash__2gpu_run_s25/anchor_s15/bank_step15.json | Configuration | 401.4 KB | — |
| grpo_qwen3-4b_ours_appworld_flash__2gpu_run_s25/anchor_s25/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_ours_appworld_flash__2gpu_run_s25/anchor_s25/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_ours_appworld_flash__2gpu_run_s25/anchor_s25/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_ours_appworld_flash__2gpu_run_s25/anchor_s25/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_ours_appworld_flash__2gpu_run_s25/anchor_s25/bank_step25.json | Configuration | 655.0 KB | — |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s30/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s30/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s30/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s30/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s30/bank_step30.json | Configuration | 552.5 KB | — |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s95/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s95/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s95/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s95/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s95/bank_step95.json | Configuration | 1.4 MB | — |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s99/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s99/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s99/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s99/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s99/bank_step99.json | Configuration | 1.4 MB | — |
| grpo_qwen3-4b_ours_appworld_luna/best/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_ours_appworld_luna/best/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_ours_appworld_luna/best/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_ours_appworld_luna/best/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_ours_appworld_luna/best/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_ours_appworld_luna/latest/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_ours_appworld_luna/latest/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_ours_appworld_luna/latest/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_ours_appworld_luna/latest/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_ours_appworld_luna/latest/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_ours_appworld_luna/rescued_s60/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_ours_appworld_luna/rescued_s60/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_ours_appworld_luna/rescued_s60/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_ours_appworld_luna/rescued_s60/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_ours_appworld_luna/rescued_s60/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_ours_appworld_luna__2gpu_run_s20/anchor_s15/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_ours_appworld_luna__2gpu_run_s20/anchor_s15/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_ours_appworld_luna__2gpu_run_s20/anchor_s15/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_ours_appworld_luna__2gpu_run_s20/anchor_s15/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_ours_appworld_luna__2gpu_run_s20/anchor_s15/bank_step15.json | Configuration | 208.1 KB | — |
| grpo_qwen3-4b_ours_appworld_luna__2gpu_run_s20/anchor_s20/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_ours_appworld_luna__2gpu_run_s20/anchor_s20/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_ours_appworld_luna__2gpu_run_s20/anchor_s20/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_ours_appworld_luna__2gpu_run_s20/anchor_s20/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_ours_appworld_luna__2gpu_run_s20/anchor_s20/bank_step20.json | Configuration | 209.9 KB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s15/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s15/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s15/actor/generation_config.json | Configuration | 187 B | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s15/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s15/bank_step15.json | Configuration | 245.2 KB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s17/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s17/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s17/actor/generation_config.json | Configuration | 187 B | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s17/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s17/bank_step17.json | Configuration | 281.3 KB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/best/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/best/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/best/generation_config.json | Configuration | 187 B | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/best/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/best/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/best_s5/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/best_s5/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/best_s5/generation_config.json | Configuration | 187 B | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/best_s5/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/best_s5/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/latest/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/latest/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/latest/generation_config.json | Configuration | 187 B | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/latest/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/latest/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_ours_appworld_luna_sft__4gpu_run_s4/anchor_s4/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_ours_appworld_luna_sft__4gpu_run_s4/anchor_s4/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft__4gpu_run_s4/anchor_s4/actor/generation_config.json | Configuration | 187 B | — |
| grpo_qwen3-4b_ours_appworld_luna_sft__4gpu_run_s4/anchor_s4/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_ours_appworld_luna_sft__4gpu_run_s4/anchor_s4/bank_step4.json | Configuration | 123.7 KB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/actor/generation_config.json | Configuration | 187 B | — |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/actor/generation_config.json | Configuration | 187 B | — |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_skillrl_alf_flash/anchor_s121/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_skillrl_alf_flash/anchor_s121/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_skillrl_alf_flash/anchor_s121/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_skillrl_alf_flash/anchor_s121/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_skillrl_alf_flash/anchor_s40/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_skillrl_alf_flash/anchor_s40/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_skillrl_alf_flash/anchor_s40/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_skillrl_alf_flash/anchor_s40/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_skillrl_alf_flash/best/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_skillrl_alf_flash/best/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_skillrl_alf_flash/best/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_skillrl_alf_flash/best/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_skillrl_alf_flash/best/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_skillrl_alf_flash/latest/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_skillrl_alf_flash/latest/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_skillrl_alf_flash/latest/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_skillrl_alf_flash/latest/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_skillrl_alf_flash/latest/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_skillrl_alf_flash/rescued_s75/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_skillrl_alf_flash/rescued_s75/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_skillrl_alf_flash/rescued_s75/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_skillrl_alf_flash/rescued_s75/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_skillrl_alf_flash/rescued_s75/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_v6_2/anchor_s160/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_v6_2/anchor_s160/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_v6_2/anchor_s160/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_v6_2/anchor_s160/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_v6_2/anchor_s190/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_v6_2/anchor_s190/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_v6_2/anchor_s190/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_v6_2/anchor_s190/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_v6_2/best/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_v6_2/best/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_v6_2/best/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_v6_2/best/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_v6_2/best/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_v6_2/latest/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_v6_2/latest/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_v6_2/latest/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_v6_2/latest/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_v6_2/latest/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s123/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s123/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s123/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s123/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s160/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s160/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s160/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s160/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s40/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s40/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s40/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s40/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/best/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/best/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/best/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/best/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/best/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/best_s60/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/best_s60/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/best_s60/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/best_s60/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/best_s60/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/latest/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/latest/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/latest/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/latest/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/latest/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s130/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s130/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s130/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s130/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s159/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s159/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s159/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s159/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s160/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s160/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s160/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s160/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s40/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s40/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s40/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s40/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/best/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/best/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/best/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/best/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/best/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/latest/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/latest/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/latest/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/latest/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/latest/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/rescued_s80/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/rescued_s80/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/rescued_s80/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/rescued_s80/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/rescued_s80/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_v6_2_r110/anchor_s160/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_v6_2_r110/anchor_s160/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_v6_2_r110/anchor_s160/actor/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_v6_2_r110/anchor_s160/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_v6_2_r110/best/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_v6_2_r110/best/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_v6_2_r110/best/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_v6_2_r110/best/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_v6_2_r110/best/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_v6_2_r110/best_s150/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_v6_2_r110/best_s150/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_v6_2_r110/best_s150/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_v6_2_r110/best_s150/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_v6_2_r110/best_s150/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_v6_2_r110/latest/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_v6_2_r110/latest/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_v6_2_r110/latest/generation_config.json | Configuration | 213 B | — |
| grpo_qwen3-4b_v6_2_r110/latest/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_v6_2_r110/latest/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_v6_2_sft/anchor_s190/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_v6_2_sft/anchor_s190/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_v6_2_sft/anchor_s190/actor/generation_config.json | Configuration | 187 B | — |
| grpo_qwen3-4b_v6_2_sft/anchor_s190/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_v6_2_sft/best/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_v6_2_sft/best/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_v6_2_sft/best/generation_config.json | Configuration | 187 B | — |
| grpo_qwen3-4b_v6_2_sft/best/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_v6_2_sft/best/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_v6_2_sft/latest/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_v6_2_sft/latest/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_v6_2_sft/latest/generation_config.json | Configuration | 187 B | — |
| grpo_qwen3-4b_v6_2_sft/latest/model.safetensors.index.json | Configuration | 32.9 KB | — |
| grpo_qwen3-4b_v6_2_sft/latest/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_v6_2_sft/rescued_best/anchor_s160_modelonly/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_v6_2_sft/rescued_best/anchor_s160_modelonly/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_v6_2_sft/rescued_best/anchor_s160_modelonly/actor/generation_config.json | Configuration | 187 B | — |
| grpo_qwen3-4b_v6_2_sft/rescued_best/anchor_s160_modelonly/actor/special_tokens_map.json | Configuration | 613 B | — |
| grpo_qwen3-4b_v6_2_sft/rescued_s160/actor/added_tokens.json | Configuration | 707 B | — |
| grpo_qwen3-4b_v6_2_sft/rescued_s160/actor/config.json | Configuration | 1.5 KB | — |
| grpo_qwen3-4b_v6_2_sft/rescued_s160/actor/generation_config.json | Configuration | 187 B | — |
| grpo_qwen3-4b_v6_2_sft/rescued_s160/actor/special_tokens_map.json | Configuration | 613 B | — |
| merged/grpo_qwen3-4b_d2skill_sft/best_s80/added_tokens.json | Configuration | 707 B | — |
| merged/grpo_qwen3-4b_d2skill_sft/best_s80/config.json | Configuration | 1.5 KB | — |
| merged/grpo_qwen3-4b_d2skill_sft/best_s80/generation_config.json | Configuration | 187 B | — |
| merged/grpo_qwen3-4b_d2skill_sft/best_s80/model.safetensors.index.json | Configuration | 32.9 KB | — |
| merged/grpo_qwen3-4b_d2skill_sft/best_s80/special_tokens_map.json | Configuration | 613 B | — |
| merged/grpo_qwen3-4b_v6_2_sft/best_s140/added_tokens.json | Configuration | 707 B | — |
| merged/grpo_qwen3-4b_v6_2_sft/best_s140/config.json | Configuration | 1.5 KB | — |
| merged/grpo_qwen3-4b_v6_2_sft/best_s140/generation_config.json | Configuration | 187 B | — |
| merged/grpo_qwen3-4b_v6_2_sft/best_s140/model.safetensors.index.json | Configuration | 32.9 KB | — |
| merged/grpo_qwen3-4b_v6_2_sft/best_s140/special_tokens_map.json | Configuration | 613 B | — |
| checkpoints/grpo_qwen3-4b_d2skill_base/global_step_10/actor/chat_template.jinja | Other | 2.6 KB | — |
| checkpoints/grpo_qwen3-4b_d2skill_base/latest_checkpointed_iteration.txt | Other | 2 B | — |
| checkpoints/grpo_qwen3-4b_d2skill_sft/best_ckpt_step40/actor/chat_template.jinja | Other | 2.6 KB | — |
| checkpoints/grpo_qwen3-4b_d2skill_sft/global_step_30/MANIFEST.sha256 | Other | 1.5 KB | — |
| checkpoints/grpo_qwen3-4b_d2skill_sft/global_step_30/SLOT_STEP.txt | Other | 189 B | — |
| checkpoints/grpo_qwen3-4b_d2skill_sft/global_step_30/actor/chat_template.jinja | Other | 2.6 KB | — |
| checkpoints/grpo_qwen3-4b_d2skill_sft/global_step_80/actor/chat_template.jinja | Other | 2.6 KB | — |
| checkpoints/grpo_qwen3-4b_d2skill_sft/latest_checkpointed_iteration.txt | Other | 2 B | — |
| checkpoints/grpo_qwen3-4b_v6/global_step_160/actor/chat_template.jinja | Other | 2.6 KB | — |
| checkpoints/grpo_qwen3-4b_v6_2/global_step_50/actor/chat_template.jinja | Other | 2.6 KB | — |
| checkpoints/grpo_qwen3-4b_v6_2/latest_checkpointed_iteration.txt | Other | 2 B | — |
| checkpoints/grpo_qwen3-4b_v6_2_sft/global_step_90/actor/chat_template.jinja | Other | 2.6 KB | — |
| checkpoints/grpo_qwen3-4b_v6_2_sft/latest_checkpointed_iteration.txt | Other | 2 B | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s123/SLOT_STEP.txt | Other | 78 B | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s123/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s30/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s40/SLOT_STEP.txt | Other | 76 B | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s40/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s80/SLOT_STEP.txt | Other | 76 B | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s80/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_appworld_grpo_base/best/SLOT_STEP.txt | Other | 73 B | — |
| grpo_qwen3-4b_appworld_grpo_base/best/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_appworld_grpo_base/latest/SLOT_STEP.txt | Other | 76 B | — |
| grpo_qwen3-4b_appworld_grpo_base/latest/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s129/SLOT_STEP.txt | Other | 231 B | — |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s129/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s130/SLOT_STEP.txt | Other | 506 B | — |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s130/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s95/SLOT_STEP.txt | Other | 227 B | — |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s95/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_appworld_skillrl_flash/anchor_s30/SLOT_STEP.txt | Other | 80 B | — |
| grpo_qwen3-4b_appworld_skillrl_flash/anchor_s30/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_appworld_skillrl_flash/anchor_s90/SLOT_STEP.txt | Other | 80 B | — |
| grpo_qwen3-4b_appworld_skillrl_flash/anchor_s90/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_appworld_skillrl_flash/best/SLOT_STEP.txt | Other | 77 B | — |
| grpo_qwen3-4b_appworld_skillrl_flash/best/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_appworld_skillrl_flash/latest/SLOT_STEP.txt | Other | 80 B | — |
| grpo_qwen3-4b_appworld_skillrl_flash/latest/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_appworld_skillrl_flash/rescued_s95/SLOT_STEP.txt | Other | 335 B | — |
| grpo_qwen3-4b_appworld_skillrl_flash/rescued_s95/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna/anchor_s30/SLOT_STEP.txt | Other | 79 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna/anchor_s30/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna/anchor_s95/SLOT_STEP.txt | Other | 79 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna/anchor_s95/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna/best/SLOT_STEP.txt | Other | 76 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna/best/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna/latest/SLOT_STEP.txt | Other | 79 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna/latest/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna/rescued_s65/SLOT_STEP.txt | Other | 230 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna/rescued_s65/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s30/SLOT_STEP.txt | Other | 83 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s30/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s90/SLOT_STEP.txt | Other | 83 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s90/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s96/SLOT_STEP.txt | Other | 83 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s96/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/best/SLOT_STEP.txt | Other | 80 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/best/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/latest/SLOT_STEP.txt | Other | 83 B | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/latest/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft_2gpu_run_s5/anchor_s5/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s30/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s68/SLOT_STEP.txt | Other | 80 B | — |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s68/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s80/SLOT_STEP.txt | Other | 80 B | — |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s80/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/best/SLOT_STEP.txt | Other | 77 B | — |
| grpo_qwen3-4b_d2skill_appworld_flash/best/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/latest/SLOT_STEP.txt | Other | 79 B | — |
| grpo_qwen3-4b_d2skill_appworld_flash/latest/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/rescued_s50/SLOT_STEP.txt | Other | 231 B | — |
| grpo_qwen3-4b_d2skill_appworld_flash/rescued_s50/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/rescued_s72/SLOT_STEP.txt | Other | 233 B | — |
| grpo_qwen3-4b_d2skill_appworld_flash/rescued_s72/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s30/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s80/SLOT_STEP.txt | Other | 79 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s80/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s85/SLOT_STEP.txt | Other | 79 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s85/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s89/SLOT_STEP.txt | Other | 79 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s89/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/best/SLOT_STEP.txt | Other | 76 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna/best/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/best_s70/SLOT_STEP.txt | Other | 76 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna/best_s70/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/latest/SLOT_STEP.txt | Other | 79 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna/latest/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/SLOT_STEP.txt | Other | 83 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/best/SLOT_STEP.txt | Other | 80 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/best/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/latest/SLOT_STEP.txt | Other | 82 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/latest/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/rescued_s23/SLOT_STEP.txt | Other | 234 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/rescued_s23/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__2gpu_run_s5/anchor_s5/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__4gpu_run_s5/anchor_s5/SLOT_STEP.txt | Other | 85 B | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__4gpu_run_s5/anchor_s5/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_d2skill_base/anchor_s120/SLOT_STEP.txt | Other | 72 B | — |
| grpo_qwen3-4b_d2skill_base/anchor_s120/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_d2skill_base/anchor_s160/SLOT_STEP.txt | Other | 63 B | — |
| grpo_qwen3-4b_d2skill_base/anchor_s160/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_d2skill_base/best/SLOT_STEP.txt | Other | 57 B | — |
| grpo_qwen3-4b_d2skill_base/best/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_d2skill_base/latest/SLOT_STEP.txt | Other | 70 B | — |
| grpo_qwen3-4b_d2skill_base/latest/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_d2skill_base/rescued_s135/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_d2skill_base/rescued_s160/MODEL_ONLY.txt | Other | 332 B | — |
| grpo_qwen3-4b_d2skill_base/rescued_s160/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_d2skill_base/rescued_s85/MODEL_ONLY.txt | Other | 332 B | — |
| grpo_qwen3-4b_d2skill_base/rescued_s85/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_d2skill_sft/best/SLOT_STEP.txt | Other | 55 B | — |
| grpo_qwen3-4b_d2skill_sft/best/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s155/SLOT_STEP.txt | Other | 75 B | — |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s155/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s160/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_d2skill_sft_b80/best/SLOT_STEP.txt | Other | 60 B | — |
| grpo_qwen3-4b_d2skill_sft_b80/best/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_d2skill_sft_b80/latest/SLOT_STEP.txt | Other | 62 B | — |
| grpo_qwen3-4b_d2skill_sft_b80/latest/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_gem_d2skill/anchor_s155/SLOT_STEP.txt | Other | 71 B | — |
| grpo_qwen3-4b_gem_d2skill/anchor_s155/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_gem_d2skill/anchor_s160/SLOT_STEP.txt | Other | 62 B | — |
| grpo_qwen3-4b_gem_d2skill/anchor_s160/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_gem_d2skill/best/SLOT_STEP.txt | Other | 56 B | — |
| grpo_qwen3-4b_gem_d2skill/best/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_gem_d2skill/latest/SLOT_STEP.txt | Other | 58 B | — |
| grpo_qwen3-4b_gem_d2skill/latest/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_gem_d2skill/rescued_s130/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_gem_v6_2/anchor_s160/SLOT_STEP.txt | Other | 68 B | — |
| grpo_qwen3-4b_gem_v6_2/anchor_s160/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_gem_v6_2/anchor_s170/SLOT_STEP.txt | Other | 68 B | — |
| grpo_qwen3-4b_gem_v6_2/anchor_s170/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_gem_v6_2/anchor_s40/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_gem_v6_2/best/SLOT_STEP.txt | Other | 64 B | — |
| grpo_qwen3-4b_gem_v6_2/best/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_gem_v6_2/latest/SLOT_STEP.txt | Other | 66 B | — |
| grpo_qwen3-4b_gem_v6_2/latest/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_gem_v6_2/rescued_s120/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s100/SLOT_STEP.txt | Other | 79 B | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s100/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s30/SLOT_STEP.txt | Other | 77 B | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s30/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s55/SLOT_STEP.txt | Other | 77 B | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s55/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s85/SLOT_STEP.txt | Other | 77 B | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s85/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_ours_appworld_flash/best/SLOT_STEP.txt | Other | 74 B | — |
| grpo_qwen3-4b_ours_appworld_flash/best/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_ours_appworld_flash/latest/SLOT_STEP.txt | Other | 77 B | — |
| grpo_qwen3-4b_ours_appworld_flash/latest/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_ours_appworld_flash__2gpu_run_s25/anchor_s15/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_ours_appworld_flash__2gpu_run_s25/anchor_s25/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s30/SLOT_STEP.txt | Other | 76 B | — |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s30/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s95/SLOT_STEP.txt | Other | 76 B | — |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s95/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s99/SLOT_STEP.txt | Other | 76 B | — |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s99/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_ours_appworld_luna/best/SLOT_STEP.txt | Other | 73 B | — |
| grpo_qwen3-4b_ours_appworld_luna/best/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_ours_appworld_luna/latest/SLOT_STEP.txt | Other | 76 B | — |
| grpo_qwen3-4b_ours_appworld_luna/latest/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_ours_appworld_luna/rescued_s60/SLOT_STEP.txt | Other | 227 B | — |
| grpo_qwen3-4b_ours_appworld_luna/rescued_s60/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_ours_appworld_luna__2gpu_run_s20/anchor_s15/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_ours_appworld_luna__2gpu_run_s20/anchor_s20/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s15/SLOT_STEP.txt | Other | 80 B | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s15/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s17/SLOT_STEP.txt | Other | 80 B | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s17/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/best/SLOT_STEP.txt | Other | 76 B | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/best/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/best_s5/SLOT_STEP.txt | Other | 76 B | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/best_s5/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/latest/SLOT_STEP.txt | Other | 79 B | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/latest/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft__4gpu_run_s4/anchor_s4/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/MANIFEST.sha256 | Other | 3.4 KB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/SLOT_STEP.txt | Other | 194 B | — |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/MANIFEST.sha256 | Other | 3.4 KB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/SLOT_STEP.txt | Other | 192 B | — |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_skillrl_alf_flash/anchor_s121/SLOT_STEP.txt | Other | 77 B | — |
| grpo_qwen3-4b_skillrl_alf_flash/anchor_s121/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_skillrl_alf_flash/anchor_s40/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_skillrl_alf_flash/best/SLOT_STEP.txt | Other | 72 B | — |
| grpo_qwen3-4b_skillrl_alf_flash/best/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_skillrl_alf_flash/latest/SLOT_STEP.txt | Other | 75 B | — |
| grpo_qwen3-4b_skillrl_alf_flash/latest/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_skillrl_alf_flash/rescued_s75/SLOT_STEP.txt | Other | 226 B | — |
| grpo_qwen3-4b_skillrl_alf_flash/rescued_s75/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_v6_2/anchor_s160/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_v6_2/anchor_s190/SLOT_STEP.txt | Other | 64 B | — |
| grpo_qwen3-4b_v6_2/anchor_s190/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_v6_2/best/SLOT_STEP.txt | Other | 60 B | — |
| grpo_qwen3-4b_v6_2/best/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_v6_2/latest/SLOT_STEP.txt | Other | 51 B | — |
| grpo_qwen3-4b_v6_2/latest/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s123/SLOT_STEP.txt | Other | 77 B | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s123/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s160/SLOT_STEP.txt | Other | 77 B | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s160/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s40/SLOT_STEP.txt | Other | 75 B | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s40/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/best/SLOT_STEP.txt | Other | 72 B | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/best/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/best_s60/SLOT_STEP.txt | Other | 72 B | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/best_s60/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/latest/SLOT_STEP.txt | Other | 75 B | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/latest/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s130/SLOT_STEP.txt | Other | 77 B | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s130/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s159/SLOT_STEP.txt | Other | 77 B | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s159/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s160/SLOT_STEP.txt | Other | 77 B | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s160/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s40/SLOT_STEP.txt | Other | 75 B | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s40/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/best/SLOT_STEP.txt | Other | 72 B | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/best/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/latest/SLOT_STEP.txt | Other | 75 B | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/latest/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/rescued_s80/SLOT_STEP.txt | Other | 226 B | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/rescued_s80/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_v6_2_r110/anchor_s160/SLOT_STEP.txt | Other | 69 B | — |
| grpo_qwen3-4b_v6_2_r110/anchor_s160/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_v6_2_r110/best/SLOT_STEP.txt | Other | 65 B | — |
| grpo_qwen3-4b_v6_2_r110/best/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_v6_2_r110/best_s150/SLOT_STEP.txt | Other | 222 B | — |
| grpo_qwen3-4b_v6_2_r110/best_s150/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_v6_2_r110/latest/SLOT_STEP.txt | Other | 67 B | — |
| grpo_qwen3-4b_v6_2_r110/latest/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_v6_2_sft/anchor_s190/SLOT_STEP.txt | Other | 68 B | — |
| grpo_qwen3-4b_v6_2_sft/anchor_s190/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_v6_2_sft/best/SLOT_STEP.txt | Other | 64 B | — |
| grpo_qwen3-4b_v6_2_sft/best/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_v6_2_sft/latest/SLOT_STEP.txt | Other | 55 B | — |
| grpo_qwen3-4b_v6_2_sft/latest/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_v6_2_sft/rescued_best/anchor_s160_modelonly/MODEL_ONLY.txt | Other | 1.1 KB | — |
| grpo_qwen3-4b_v6_2_sft/rescued_best/anchor_s160_modelonly/actor/chat_template.jinja | Other | 2.6 KB | — |
| grpo_qwen3-4b_v6_2_sft/rescued_s160/MODEL_ONLY.txt | Other | 1.1 KB | — |
| grpo_qwen3-4b_v6_2_sft/rescued_s160/SLOT_STEP.txt | Other | 371 B | — |
| grpo_qwen3-4b_v6_2_sft/rescued_s160/actor/chat_template.jinja | Other | 2.6 KB | — |
| merged/grpo_qwen3-4b_d2skill_sft/best_s80/chat_template.jinja | Other | 2.6 KB | — |
| merged/grpo_qwen3-4b_v6_2_sft/best_s140/chat_template.jinja | Other | 2.6 KB | — |
| package1/MANIFEST.tsv | Other | 4.9 MB | — |
| package1/SHA256SUMS.package1.txt | Other | 264 B | — |
| package1/code_data.tar | Other | 2.8 GB | a1f4b7411364 |
| package1/expdirs.tar | Other | 3.3 GB | 9370af816782 |
| package1/launchers_relocatable/launch_d2skill_alf_base.sh | Other | 7.5 KB | — |
| package1/launchers_relocatable/launch_d2skill_alf_sft.sh | Other | 7.6 KB | — |
| package1/launchers_relocatable/launch_v6_2.sh | Other | 6.4 KB | — |
| package1/launchers_relocatable/launch_v6_2_sft.sh | Other | 7.1 KB | — |
| package1/launchers_relocatable/preflight_d2skill_base.sh | Other | 2.0 KB | — |
| package1/launchers_relocatable/preflight_v62.sh | Other | 2.2 KB | — |
| package1/launchers_relocatable/ray_pending_check.sh | Other | 1.5 KB | — |
| package1/launchers_relocatable/run_trackable_v4_supervised_capped.sh | Other | 9.4 KB | — |
| package1/sft_alfworld_full_ck1084.tar | Other | 8.1 GB | 8b7cbaa049f3 |
| package2/SHA256SUMS.package2.txt | Other | 445 B | — |
| .gitattributes | Repository | 14.9 KB | — |
| checkpoints/grpo_qwen3-4b_d2skill_base/global_step_10/actor/merges.txt | Tokenizer | 1.7 MB | — |
| checkpoints/grpo_qwen3-4b_d2skill_base/global_step_10/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| checkpoints/grpo_qwen3-4b_d2skill_base/global_step_10/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| checkpoints/grpo_qwen3-4b_d2skill_base/global_step_10/actor/vocab.json | Tokenizer | 2.8 MB | — |
| checkpoints/grpo_qwen3-4b_d2skill_sft/best_ckpt_step40/actor/merges.txt | Tokenizer | 1.7 MB | — |
| checkpoints/grpo_qwen3-4b_d2skill_sft/best_ckpt_step40/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| checkpoints/grpo_qwen3-4b_d2skill_sft/best_ckpt_step40/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| checkpoints/grpo_qwen3-4b_d2skill_sft/best_ckpt_step40/actor/vocab.json | Tokenizer | 2.8 MB | — |
| checkpoints/grpo_qwen3-4b_d2skill_sft/global_step_30/actor/merges.txt | Tokenizer | 1.7 MB | — |
| checkpoints/grpo_qwen3-4b_d2skill_sft/global_step_30/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| checkpoints/grpo_qwen3-4b_d2skill_sft/global_step_30/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| checkpoints/grpo_qwen3-4b_d2skill_sft/global_step_30/actor/vocab.json | Tokenizer | 2.8 MB | — |
| checkpoints/grpo_qwen3-4b_d2skill_sft/global_step_80/actor/merges.txt | Tokenizer | 1.7 MB | — |
| checkpoints/grpo_qwen3-4b_d2skill_sft/global_step_80/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| checkpoints/grpo_qwen3-4b_d2skill_sft/global_step_80/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| checkpoints/grpo_qwen3-4b_d2skill_sft/global_step_80/actor/vocab.json | Tokenizer | 2.8 MB | — |
| checkpoints/grpo_qwen3-4b_v6/global_step_160/actor/merges.txt | Tokenizer | 1.7 MB | — |
| checkpoints/grpo_qwen3-4b_v6/global_step_160/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| checkpoints/grpo_qwen3-4b_v6/global_step_160/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| checkpoints/grpo_qwen3-4b_v6/global_step_160/actor/vocab.json | Tokenizer | 2.8 MB | — |
| checkpoints/grpo_qwen3-4b_v6_2/global_step_50/actor/merges.txt | Tokenizer | 1.7 MB | — |
| checkpoints/grpo_qwen3-4b_v6_2/global_step_50/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| checkpoints/grpo_qwen3-4b_v6_2/global_step_50/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| checkpoints/grpo_qwen3-4b_v6_2/global_step_50/actor/vocab.json | Tokenizer | 2.8 MB | — |
| checkpoints/grpo_qwen3-4b_v6_2_sft/global_step_90/actor/merges.txt | Tokenizer | 1.7 MB | — |
| checkpoints/grpo_qwen3-4b_v6_2_sft/global_step_90/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| checkpoints/grpo_qwen3-4b_v6_2_sft/global_step_90/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| checkpoints/grpo_qwen3-4b_v6_2_sft/global_step_90/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s123/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s123/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s123/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s123/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s30/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s30/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s30/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s30/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s40/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s40/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s40/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s40/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s80/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s80/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s80/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_appworld_grpo_base/anchor_s80/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_appworld_grpo_base/best/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_appworld_grpo_base/best/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_appworld_grpo_base/best/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_appworld_grpo_base/best/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_appworld_grpo_base/latest/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_appworld_grpo_base/latest/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_appworld_grpo_base/latest/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_appworld_grpo_base/latest/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s129/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s129/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s129/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s129/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s130/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s130/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s130/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s130/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s95/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s95/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s95/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_appworld_grpo_base/rescued_s95/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_appworld_skillrl_flash/anchor_s30/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_appworld_skillrl_flash/anchor_s30/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_appworld_skillrl_flash/anchor_s30/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_appworld_skillrl_flash/anchor_s30/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_appworld_skillrl_flash/anchor_s90/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_appworld_skillrl_flash/anchor_s90/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_appworld_skillrl_flash/anchor_s90/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_appworld_skillrl_flash/anchor_s90/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_appworld_skillrl_flash/best/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_appworld_skillrl_flash/best/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_appworld_skillrl_flash/best/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_appworld_skillrl_flash/best/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_appworld_skillrl_flash/latest/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_appworld_skillrl_flash/latest/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_appworld_skillrl_flash/latest/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_appworld_skillrl_flash/latest/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_appworld_skillrl_flash/rescued_s95/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_appworld_skillrl_flash/rescued_s95/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_appworld_skillrl_flash/rescued_s95/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_appworld_skillrl_flash/rescued_s95/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_appworld_skillrl_luna/anchor_s30/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_appworld_skillrl_luna/anchor_s30/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_appworld_skillrl_luna/anchor_s30/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna/anchor_s30/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_appworld_skillrl_luna/anchor_s95/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_appworld_skillrl_luna/anchor_s95/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_appworld_skillrl_luna/anchor_s95/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna/anchor_s95/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_appworld_skillrl_luna/best/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_appworld_skillrl_luna/best/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_appworld_skillrl_luna/best/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna/best/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_appworld_skillrl_luna/latest/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_appworld_skillrl_luna/latest/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_appworld_skillrl_luna/latest/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna/latest/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_appworld_skillrl_luna/rescued_s65/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_appworld_skillrl_luna/rescued_s65/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_appworld_skillrl_luna/rescued_s65/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna/rescued_s65/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s30/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s30/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s30/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s30/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s90/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s90/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s90/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s90/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s96/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s96/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s96/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/anchor_s96/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/best/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/best/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/best/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/best/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/latest/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/latest/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/latest/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft/latest/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft_2gpu_run_s5/anchor_s5/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft_2gpu_run_s5/anchor_s5/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_appworld_skillrl_luna_sft_2gpu_run_s5/anchor_s5/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_appworld_skillrl_luna_sft_2gpu_run_s5/anchor_s5/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s30/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s30/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s30/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s30/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s68/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s68/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s68/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s68/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s80/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s80/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s80/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/anchor_s80/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/best/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/best/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_d2skill_appworld_flash/best/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/best/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/latest/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/latest/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_d2skill_appworld_flash/latest/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/latest/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/rescued_s50/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/rescued_s50/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_d2skill_appworld_flash/rescued_s50/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/rescued_s50/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/rescued_s72/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/rescued_s72/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_d2skill_appworld_flash/rescued_s72/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_d2skill_appworld_flash/rescued_s72/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s30/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s30/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s30/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s30/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s80/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s80/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s80/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s80/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s85/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s85/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s85/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s85/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s89/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s89/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s89/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/anchor_s89/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/best/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/best/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_d2skill_appworld_luna/best/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/best/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/best_s70/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/best_s70/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_d2skill_appworld_luna/best_s70/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/best_s70/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/latest/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/latest/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_d2skill_appworld_luna/latest/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna/latest/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/anchor_s32/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/best/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/best/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/best/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/best/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/latest/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/latest/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/latest/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/latest/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/rescued_s23/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/rescued_s23/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/rescued_s23/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft/rescued_s23/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__2gpu_run_s5/anchor_s5/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__2gpu_run_s5/anchor_s5/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__2gpu_run_s5/anchor_s5/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__2gpu_run_s5/anchor_s5/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__4gpu_run_s5/anchor_s5/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__4gpu_run_s5/anchor_s5/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__4gpu_run_s5/anchor_s5/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_d2skill_appworld_luna_sft__4gpu_run_s5/anchor_s5/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_d2skill_base/anchor_s120/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_d2skill_base/anchor_s120/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_d2skill_base/anchor_s120/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_d2skill_base/anchor_s120/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_d2skill_base/anchor_s160/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_d2skill_base/anchor_s160/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_d2skill_base/anchor_s160/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_d2skill_base/anchor_s160/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_d2skill_base/best/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_d2skill_base/best/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_d2skill_base/best/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_d2skill_base/best/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_d2skill_base/latest/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_d2skill_base/latest/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_d2skill_base/latest/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_d2skill_base/latest/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_d2skill_base/rescued_s135/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_d2skill_base/rescued_s135/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_d2skill_base/rescued_s135/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_d2skill_base/rescued_s135/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_d2skill_base/rescued_s160/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_d2skill_base/rescued_s160/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_d2skill_base/rescued_s160/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_d2skill_base/rescued_s160/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_d2skill_base/rescued_s85/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_d2skill_base/rescued_s85/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_d2skill_base/rescued_s85/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_d2skill_base/rescued_s85/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_d2skill_sft/best/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_d2skill_sft/best/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_d2skill_sft/best/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_d2skill_sft/best/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s155/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s155/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s155/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s155/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s160/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s160/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s160/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_d2skill_sft_b80/anchor_s160/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_d2skill_sft_b80/best/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_d2skill_sft_b80/best/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_d2skill_sft_b80/best/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_d2skill_sft_b80/best/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_d2skill_sft_b80/latest/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_d2skill_sft_b80/latest/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_d2skill_sft_b80/latest/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_d2skill_sft_b80/latest/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_gem_d2skill/anchor_s155/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_gem_d2skill/anchor_s155/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_gem_d2skill/anchor_s155/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_gem_d2skill/anchor_s155/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_gem_d2skill/anchor_s160/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_gem_d2skill/anchor_s160/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_gem_d2skill/anchor_s160/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_gem_d2skill/anchor_s160/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_gem_d2skill/best/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_gem_d2skill/best/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_gem_d2skill/best/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_gem_d2skill/best/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_gem_d2skill/latest/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_gem_d2skill/latest/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_gem_d2skill/latest/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_gem_d2skill/latest/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_gem_d2skill/rescued_s130/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_gem_d2skill/rescued_s130/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_gem_d2skill/rescued_s130/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_gem_d2skill/rescued_s130/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_gem_v6_2/anchor_s160/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_gem_v6_2/anchor_s160/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_gem_v6_2/anchor_s160/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_gem_v6_2/anchor_s160/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_gem_v6_2/anchor_s170/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_gem_v6_2/anchor_s170/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_gem_v6_2/anchor_s170/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_gem_v6_2/anchor_s170/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_gem_v6_2/anchor_s40/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_gem_v6_2/anchor_s40/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_gem_v6_2/anchor_s40/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_gem_v6_2/anchor_s40/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_gem_v6_2/best/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_gem_v6_2/best/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_gem_v6_2/best/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_gem_v6_2/best/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_gem_v6_2/latest/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_gem_v6_2/latest/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_gem_v6_2/latest/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_gem_v6_2/latest/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_gem_v6_2/rescued_s120/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_gem_v6_2/rescued_s120/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_gem_v6_2/rescued_s120/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_gem_v6_2/rescued_s120/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s100/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s100/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s100/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s100/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s30/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s30/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s30/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s30/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s55/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s55/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s55/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s55/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s85/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s85/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s85/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_ours_appworld_flash/anchor_s85/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_ours_appworld_flash/best/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_ours_appworld_flash/best/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_ours_appworld_flash/best/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_ours_appworld_flash/best/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_ours_appworld_flash/latest/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_ours_appworld_flash/latest/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_ours_appworld_flash/latest/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_ours_appworld_flash/latest/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_ours_appworld_flash__2gpu_run_s25/anchor_s15/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_ours_appworld_flash__2gpu_run_s25/anchor_s15/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_ours_appworld_flash__2gpu_run_s25/anchor_s15/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_ours_appworld_flash__2gpu_run_s25/anchor_s15/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_ours_appworld_flash__2gpu_run_s25/anchor_s25/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_ours_appworld_flash__2gpu_run_s25/anchor_s25/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_ours_appworld_flash__2gpu_run_s25/anchor_s25/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_ours_appworld_flash__2gpu_run_s25/anchor_s25/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s30/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s30/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s30/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s30/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s95/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s95/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s95/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s95/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s99/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s99/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s99/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_ours_appworld_luna/anchor_s99/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_ours_appworld_luna/best/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_ours_appworld_luna/best/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_ours_appworld_luna/best/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_ours_appworld_luna/best/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_ours_appworld_luna/latest/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_ours_appworld_luna/latest/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_ours_appworld_luna/latest/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_ours_appworld_luna/latest/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_ours_appworld_luna/rescued_s60/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_ours_appworld_luna/rescued_s60/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_ours_appworld_luna/rescued_s60/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_ours_appworld_luna/rescued_s60/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_ours_appworld_luna__2gpu_run_s20/anchor_s15/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_ours_appworld_luna__2gpu_run_s20/anchor_s15/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_ours_appworld_luna__2gpu_run_s20/anchor_s15/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_ours_appworld_luna__2gpu_run_s20/anchor_s15/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_ours_appworld_luna__2gpu_run_s20/anchor_s20/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_ours_appworld_luna__2gpu_run_s20/anchor_s20/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_ours_appworld_luna__2gpu_run_s20/anchor_s20/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_ours_appworld_luna__2gpu_run_s20/anchor_s20/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s15/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s15/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s15/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s15/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s17/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s17/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s17/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/anchor_s17/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/best/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/best/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_ours_appworld_luna_sft/best/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/best/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/best_s5/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/best_s5/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_ours_appworld_luna_sft/best_s5/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/best_s5/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/latest/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/latest/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_ours_appworld_luna_sft/latest/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft/latest/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft__4gpu_run_s4/anchor_s4/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft__4gpu_run_s4/anchor_s4/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_ours_appworld_luna_sft__4gpu_run_s4/anchor_s4/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft__4gpu_run_s4/anchor_s4/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s15/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_ours_appworld_luna_sft__b300_traj113771/best_s5/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_skillrl_alf_flash/anchor_s121/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_skillrl_alf_flash/anchor_s121/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_skillrl_alf_flash/anchor_s121/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_skillrl_alf_flash/anchor_s121/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_skillrl_alf_flash/anchor_s40/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_skillrl_alf_flash/anchor_s40/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_skillrl_alf_flash/anchor_s40/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_skillrl_alf_flash/anchor_s40/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_skillrl_alf_flash/best/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_skillrl_alf_flash/best/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_skillrl_alf_flash/best/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_skillrl_alf_flash/best/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_skillrl_alf_flash/latest/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_skillrl_alf_flash/latest/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_skillrl_alf_flash/latest/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_skillrl_alf_flash/latest/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_skillrl_alf_flash/rescued_s75/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_skillrl_alf_flash/rescued_s75/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_skillrl_alf_flash/rescued_s75/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_skillrl_alf_flash/rescued_s75/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_v6_2/anchor_s160/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_v6_2/anchor_s160/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_v6_2/anchor_s160/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_v6_2/anchor_s160/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_v6_2/anchor_s190/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_v6_2/anchor_s190/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_v6_2/anchor_s190/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_v6_2/anchor_s190/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_v6_2/best/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_v6_2/best/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_v6_2/best/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_v6_2/best/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_v6_2/latest/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_v6_2/latest/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_v6_2/latest/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_v6_2/latest/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s123/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s123/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s123/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s123/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s160/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s160/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s160/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s160/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s40/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s40/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s40/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/anchor_s40/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/best/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/best/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_v6_2_ablA1_bundle/best/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/best/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/best_s60/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/best_s60/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_v6_2_ablA1_bundle/best_s60/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/best_s60/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/latest/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/latest/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_v6_2_ablA1_bundle/latest/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_v6_2_ablA1_bundle/latest/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s130/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s130/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s130/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s130/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s159/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s159/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s159/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s159/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s160/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s160/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s160/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s160/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s40/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s40/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s40/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/anchor_s40/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/best/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/best/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/best/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/best/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/latest/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/latest/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/latest/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/latest/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/rescued_s80/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/rescued_s80/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/rescued_s80/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_v6_2_ablA8_nomgmt/rescued_s80/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_v6_2_r110/anchor_s160/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_v6_2_r110/anchor_s160/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_v6_2_r110/anchor_s160/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_v6_2_r110/anchor_s160/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_v6_2_r110/best/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_v6_2_r110/best/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_v6_2_r110/best/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_v6_2_r110/best/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_v6_2_r110/best_s150/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_v6_2_r110/best_s150/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_v6_2_r110/best_s150/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_v6_2_r110/best_s150/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_v6_2_r110/latest/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_v6_2_r110/latest/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_v6_2_r110/latest/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_v6_2_r110/latest/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_v6_2_sft/anchor_s190/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_v6_2_sft/anchor_s190/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_v6_2_sft/anchor_s190/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_v6_2_sft/anchor_s190/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_v6_2_sft/best/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_v6_2_sft/best/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_v6_2_sft/best/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_v6_2_sft/best/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_v6_2_sft/latest/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_v6_2_sft/latest/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_v6_2_sft/latest/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_v6_2_sft/latest/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_v6_2_sft/rescued_best/anchor_s160_modelonly/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_v6_2_sft/rescued_best/anchor_s160_modelonly/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_v6_2_sft/rescued_best/anchor_s160_modelonly/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_v6_2_sft/rescued_best/anchor_s160_modelonly/actor/vocab.json | Tokenizer | 2.8 MB | — |
| grpo_qwen3-4b_v6_2_sft/rescued_s160/actor/merges.txt | Tokenizer | 1.7 MB | — |
| grpo_qwen3-4b_v6_2_sft/rescued_s160/actor/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| grpo_qwen3-4b_v6_2_sft/rescued_s160/actor/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| grpo_qwen3-4b_v6_2_sft/rescued_s160/actor/vocab.json | Tokenizer | 2.8 MB | — |
| merged/grpo_qwen3-4b_d2skill_sft/best_s80/merges.txt | Tokenizer | 1.7 MB | — |
| merged/grpo_qwen3-4b_d2skill_sft/best_s80/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| merged/grpo_qwen3-4b_d2skill_sft/best_s80/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| merged/grpo_qwen3-4b_d2skill_sft/best_s80/vocab.json | Tokenizer | 2.8 MB | — |
| merged/grpo_qwen3-4b_v6_2_sft/best_s140/merges.txt | Tokenizer | 1.7 MB | — |
| merged/grpo_qwen3-4b_v6_2_sft/best_s140/tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| merged/grpo_qwen3-4b_v6_2_sft/best_s140/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| merged/grpo_qwen3-4b_v6_2_sft/best_s140/vocab.json | Tokenizer | 2.8 MB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 4.1 TB
Download from Yuanlin Duan
Released by Yuanlin Duan through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 4.1 TB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.