| _app | | | 212 items |
| _toctree.yml | 3.38 kB | | 9da8f3eb |
| async_grpo_trainer.html | 108 kB | | dec47b1f |
| async_grpo_trainer.md | 12.3 kB | | 0f62c989 |
| bco_trainer.html | 130 kB | | df9bb715 |
| bco_trainer.md | 14.1 kB | | 291be9aa |
| bema_for_reference_model.html | 90 kB | | af63ce66 |
| bema_for_reference_model.md | 7.18 kB | | e5761d8f |
| callbacks.html | 95.8 kB | | 824da3ed |
| callbacks.md | 7.88 kB | | e8dfceeb |
| chat_template_utils.html | 45.9 kB | | 4d1fa659 |
| chat_template_utils.md | 5.51 kB | | c6100ab5 |
| chat_templates.html | 33.5 kB | | ae399964 |
| chat_templates.md | 6.03 kB | | 64bda0d2 |
| clis.html | 53.4 kB | | 6a323596 |
| clis.md | 12.8 kB | | 139dfcd7 |
| community_tutorials.html | 31 kB | | beb00d54 |
| community_tutorials.md | 11 kB | | 6c4eae99 |
| cpo_trainer.html | 144 kB | | a45b51b1 |
| cpo_trainer.md | 23 kB | | 66e7ae7a |
| customization.html | 31 kB | | 46f167e5 |
| customization.md | 4.08 kB | | a030e951 |
| data_utils.html | 62.7 kB | | 94b67700 |
| data_utils.md | 6.87 kB | | a3f8a4f9 |
| dataset_formats.html | 223 kB | | b460c1cb |
| dataset_formats.md | 40.2 kB | | 5034c8cf |
| deepspeed_integration.html | 15.8 kB | | 3379dbc6 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 161 kB | | a307de5e |
| distillation_trainer.md | 12.3 kB | | 72764cfd |
| distributing_training.html | 96.5 kB | | 8998581c |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 233 kB | | ba31cc33 |
| dpo_trainer.md | 30.8 kB | | 3a310d4e |
| example_overview.html | 42.7 kB | | 94834c1f |
| example_overview.md | 19.7 kB | | 20df5fd9 |
| experimental_overview.html | 10.8 kB | | a2a576ec |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 85 kB | | 340d86e2 |
| gfpo.md | 5.24 kB | | 1b21b72e |
| gkd_trainer.html | 119 kB | | d8dd8982 |
| gkd_trainer.md | 14.1 kB | | a775e4b7 |
| gold_trainer.html | 166 kB | | c8b42c6f |
| gold_trainer.md | 18.1 kB | | 595d6d12 |
| grpo_trainer.html | 561 kB | | 797c1c96 |
| grpo_trainer.md | 55.8 kB | | 69c72dc8 |
| grpo_with_replay_buffer.html | 90.3 kB | | c9e502f3 |
| grpo_with_replay_buffer.md | 6.16 kB | | bab2a1cb |
| gspo_token.html | 50.2 kB | | 6e5cc614 |
| gspo_token.md | 4.27 kB | | 3a6bd762 |
| index.html | 29 kB | | 8092c151 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 1ea023bc |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 039b6bb2 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | fcf4982f |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 138 kB | | eb0386e6 |
| kto_trainer.md | 18.3 kB | | fe7d469e |
| liger_kernel_integration.html | 15 kB | | 0e728d14 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 867 kB | | e621913f |
| llms.txt | 5.15 kB | | 291c8fe5 |
| lora_without_regret.html | 45 kB | | b9ac0c09 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | a631fc0b |
| merge_model_callback.md | 1.19 kB | | fa2457db |
| minillm_trainer.html | 180 kB | | 804f8c54 |
| minillm_trainer.md | 16.4 kB | | 14eda505 |
| nash_md_trainer.html | 125 kB | | 590bac08 |
| nash_md_trainer.md | 16.3 kB | | ee822b5b |
| nemo_gym.html | 58.5 kB | | 5ebc51b9 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.45 kB | | 1f968c56 |
| online_dpo_trainer.html | 180 kB | | 0c1f1f38 |
| online_dpo_trainer.md | 23.1 kB | | 8a8618d5 |
| openenv.html | 114 kB | | f4377afd |
| openenv.md | 27.8 kB | | 5623600f |
| orpo_trainer.html | 127 kB | | 12009807 |
| orpo_trainer.md | 17.7 kB | | 99323b9f |
| paper_index.html | 742 kB | | f00c433d |
| paper_index.md | 19.1 kB | | 1f97a67a |
| papo_trainer.html | 112 kB | | 6701520a |
| papo_trainer.md | 8.82 kB | | 88e49e20 |
| peft_integration.html | 131 kB | | c85bdd25 |
| peft_integration.md | 23.9 kB | | d695471f |
| ppo_trainer.html | 279 kB | | 7d3ebff5 |
| ppo_trainer.md | 41.4 kB | | 18fac747 |
| prm_trainer.html | 118 kB | | 043e842f |
| prm_trainer.md | 13.9 kB | | e89c4bfe |
| ptt_integration.html | 29.3 kB | | ac1b0f05 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 53243f39 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 95.4 kB | | e58f3e95 |
| rapidfire_integration.md | 17.7 kB | | 08fed5af |
| reducing_memory_usage.html | 52.4 kB | | de98ddc7 |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
|