| _app | | | 311 items |
| _toctree.yml | 3.38 kB | | 9da8f3eb |
| async_grpo_trainer.html | 108 kB | | 137ce8d9 |
| async_grpo_trainer.md | 12.3 kB | | 35224f49 |
| bco_trainer.html | 130 kB | | 356cd9eb |
| bco_trainer.md | 14.1 kB | | ddd7b3cd |
| bema_for_reference_model.html | 90 kB | | 503f6970 |
| bema_for_reference_model.md | 7.18 kB | | e8be136e |
| callbacks.html | 95.8 kB | | 39308a87 |
| callbacks.md | 7.88 kB | | b3993c66 |
| chat_template_utils.html | 46.2 kB | | 78650047 |
| chat_template_utils.md | 5.77 kB | | 7e00c0b4 |
| chat_templates.html | 35.4 kB | | 64244db8 |
| chat_templates.md | 6.48 kB | | a06ad7a2 |
| clis.html | 53.4 kB | | cf3606cd |
| clis.md | 12.8 kB | | 6869cdc2 |
| community_tutorials.html | 31 kB | | ef466c04 |
| community_tutorials.md | 11 kB | | 82201c45 |
| cpo_trainer.html | 144 kB | | 5ec9c1a4 |
| cpo_trainer.md | 23 kB | | 404d4add |
| customization.html | 31 kB | | ac8b9d6f |
| customization.md | 4.08 kB | | fc69eb60 |
| data_utils.html | 62.7 kB | | ad33d633 |
| data_utils.md | 6.87 kB | | 2863ffd9 |
| dataset_formats.html | 223 kB | | b25cdee8 |
| dataset_formats.md | 40.2 kB | | 5426276a |
| deepspeed_integration.html | 15.8 kB | | 9e1ed84d |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 161 kB | | d8072341 |
| distillation_trainer.md | 12.3 kB | | 21b5b14f |
| distributing_training.html | 96.5 kB | | 5912564d |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 233 kB | | ac581a52 |
| dpo_trainer.md | 30.8 kB | | 7b0664d0 |
| example_overview.html | 42.8 kB | | b1355aa4 |
| example_overview.md | 19.7 kB | | 18c8a485 |
| experimental_overview.html | 10.8 kB | | b9492c70 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 85 kB | | c2f2f430 |
| gfpo.md | 5.24 kB | | e8744ac5 |
| gkd_trainer.html | 119 kB | | 6556d5f0 |
| gkd_trainer.md | 14.1 kB | | 827542db |
| gold_trainer.html | 166 kB | | 20292184 |
| gold_trainer.md | 18.1 kB | | 6ca67a3f |
| grpo_trainer.html | 561 kB | | 12670dfe |
| grpo_trainer.md | 55.9 kB | | 8837283e |
| grpo_with_replay_buffer.html | 90.3 kB | | cc8494ef |
| grpo_with_replay_buffer.md | 6.16 kB | | 0a77df3d |
| gspo_token.html | 50.2 kB | | ad9a388e |
| gspo_token.md | 4.27 kB | | 77a845c0 |
| index.html | 29 kB | | 09c57061 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | dad986d3 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | ede4d3e4 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | 47f6a97c |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 138 kB | | 48c79b8b |
| kto_trainer.md | 18.3 kB | | 1b57fb38 |
| liger_kernel_integration.html | 15 kB | | 0ea855a8 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 868 kB | | e6531078 |
| llms.txt | 5.15 kB | | e5ddb131 |
| lora_without_regret.html | 45 kB | | 094710cc |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 7b8f1402 |
| merge_model_callback.md | 1.19 kB | | 83e1040f |
| minillm_trainer.html | 180 kB | | d2cd9ce2 |
| minillm_trainer.md | 16.4 kB | | aee6518f |
| nash_md_trainer.html | 125 kB | | 9f80c0a6 |
| nash_md_trainer.md | 16.3 kB | | 6e17e02b |
| nemo_gym.html | 58.5 kB | | a6cbdfcf |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.45 kB | | b3a34c11 |
| online_dpo_trainer.html | 180 kB | | 0357e7c5 |
| online_dpo_trainer.md | 23.1 kB | | 6c9a8041 |
| openenv.html | 114 kB | | f3c7d2bd |
| openenv.md | 27.8 kB | | 7a211dcb |
| orpo_trainer.html | 127 kB | | 03a0db79 |
| orpo_trainer.md | 17.7 kB | | 0dfb4554 |
| paper_index.html | 742 kB | | 61f0b652 |
| paper_index.md | 19.1 kB | | c0ef4e88 |
| papo_trainer.html | 112 kB | | ff73ef7b |
| papo_trainer.md | 8.82 kB | | 45063489 |
| peft_integration.html | 131 kB | | eab67d43 |
| peft_integration.md | 23.9 kB | | f45447b5 |
| ppo_trainer.html | 279 kB | | be478ca4 |
| ppo_trainer.md | 41.4 kB | | afcbd2b6 |
| prm_trainer.html | 118 kB | | b49b6859 |
| prm_trainer.md | 13.9 kB | | b9b7de09 |
| ptt_integration.html | 29.3 kB | | 1d7da51d |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 97b4464e |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 95.4 kB | | 6dc488b9 |
| rapidfire_integration.md | 17.7 kB | | 08fed5af |
| reducing_memory_usage.html | 52.4 kB | | 7a518466 |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
|