| _app | | | 156 items |
| _toctree.yml | 3.29 kB | | 4ea3f42b |
| async_grpo_trainer.html | 108 kB | | 8af7bf48 |
| async_grpo_trainer.md | 12.3 kB | | 990eb980 |
| bco_trainer.html | 131 kB | | fb82739f |
| bco_trainer.md | 14.4 kB | | d5c4c532 |
| bema_for_reference_model.html | 90 kB | | 70bc8e02 |
| bema_for_reference_model.md | 7.18 kB | | 716533c7 |
| callbacks.html | 95.8 kB | | 1c01fd06 |
| callbacks.md | 7.88 kB | | 2b22535b |
| chat_template_utils.html | 43.9 kB | | a4d83b78 |
| chat_template_utils.md | 4.65 kB | | 1209fc14 |
| clis.html | 53.4 kB | | 345adcf2 |
| clis.md | 12.8 kB | | 64e44aeb |
| community_tutorials.html | 31.1 kB | | 30b9ce4e |
| community_tutorials.md | 11 kB | | 17e39bff |
| cpo_trainer.html | 146 kB | | 475c0fc8 |
| cpo_trainer.md | 23.2 kB | | 2bb8bce0 |
| customization.html | 31 kB | | e42440b3 |
| customization.md | 4.08 kB | | 9cf6a48f |
| data_utils.html | 62.9 kB | | b4963a61 |
| data_utils.md | 6.32 kB | | a3ceeb61 |
| dataset_formats.html | 223 kB | | 7419a9f0 |
| dataset_formats.md | 40.2 kB | | d80171a5 |
| deepspeed_integration.html | 15.8 kB | | 4af66f28 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distributing_training.html | 96.5 kB | | 792ccf3e |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | 4121251d |
| dpo_trainer.md | 30.7 kB | | 25e40710 |
| example_overview.html | 42.7 kB | | e0962993 |
| example_overview.md | 19.7 kB | | 02b2417a |
| experimental_overview.html | 10.8 kB | | 54e0e342 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | 12f8e40c |
| gfpo.md | 5.24 kB | | d0ade890 |
| gkd_trainer.html | 119 kB | | fbae843c |
| gkd_trainer.md | 14.1 kB | | a8a97bd8 |
| gold_trainer.html | 156 kB | | f6b59c04 |
| gold_trainer.md | 16.8 kB | | 51190fa5 |
| grpo_trainer.html | 555 kB | | 45bb5f17 |
| grpo_trainer.md | 54 kB | | b6f4cf65 |
| grpo_with_replay_buffer.html | 89.6 kB | | 15350973 |
| grpo_with_replay_buffer.md | 6.16 kB | | 0ed29294 |
| gspo_token.html | 50.2 kB | | 446a81bd |
| gspo_token.md | 4.27 kB | | 5d860bd9 |
| index.html | 28.8 kB | | d38d06a3 |
| index.md | 3.68 kB | | 55bdb9e3 |
| installation.html | 13.9 kB | | 60b99905 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 5a2964d0 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| judges.html | 122 kB | | 4412097a |
| judges.md | 15.8 kB | | d3751521 |
| kernels_hub.html | 26.8 kB | | 8c857e6e |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 138 kB | | 31673e17 |
| kto_trainer.md | 19.4 kB | | 773b90dc |
| liger_kernel_integration.html | 15 kB | | 8fa2200c |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 832 kB | | 8942b6d1 |
| llms.txt | 5.04 kB | | b7c3ff40 |
| lora_without_regret.html | 45 kB | | db7de9f2 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 3406cc60 |
| merge_model_callback.md | 1.19 kB | | a6488fd1 |
| minillm_trainer.html | 179 kB | | 23d4d45f |
| minillm_trainer.md | 16.4 kB | | 0f5d699c |
| nash_md_trainer.html | 130 kB | | 179d07dd |
| nash_md_trainer.md | 17.1 kB | | 87ff7175 |
| nemo_gym.html | 58.5 kB | | 57ef49a0 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.45 kB | | 529b650a |
| online_dpo_trainer.html | 195 kB | | 85660ae3 |
| online_dpo_trainer.md | 26.3 kB | | 194ed7c9 |
| openenv.html | 114 kB | | 28a49183 |
| openenv.md | 27.8 kB | | c9519360 |
| orpo_trainer.html | 129 kB | | 5986d483 |
| orpo_trainer.md | 17.9 kB | | 29ea0e03 |
| paper_index.html | 732 kB | | c0bb4172 |
| paper_index.md | 17 kB | | 8861296d |
| papo_trainer.html | 111 kB | | fea6c8cf |
| papo_trainer.md | 8.82 kB | | 50b113f0 |
| peft_integration.html | 131 kB | | d9323000 |
| peft_integration.md | 23.9 kB | | 0c9204cf |
| ppo_trainer.html | 280 kB | | 68bdcfb9 |
| ppo_trainer.md | 42 kB | | 8a7d8c5e |
| prm_trainer.html | 117 kB | | a7ef4132 |
| prm_trainer.md | 13.9 kB | | c84dc4fe |
| ptt_integration.html | 29.3 kB | | 99e387bf |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | b3542491 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | 43e3bc85 |
| rapidfire_integration.md | 12.8 kB | | c14e6d99 |
| reducing_memory_usage.html | 52.4 kB | | aa3db3d4 |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
| reward_trainer.html | 175 kB | | e7e565f4 |
| reward_trainer.md | 21.5 kB | | 6eccb45a |
|