| _app | | | 150 items |
| _toctree.yml | 3.38 kB | | 9da8f3eb |
| async_grpo_trainer.html | 108 kB | | cc7191d5 |
| async_grpo_trainer.md | 12.3 kB | | aaea5501 |
| bco_trainer.html | 130 kB | | dc602a1d |
| bco_trainer.md | 14.1 kB | | 673cd2b0 |
| bema_for_reference_model.html | 90 kB | | 9fc1e861 |
| bema_for_reference_model.md | 7.18 kB | | 9bfeab54 |
| callbacks.html | 95.8 kB | | a542bc47 |
| callbacks.md | 7.88 kB | | d25cc0ec |
| chat_template_utils.html | 45.8 kB | | 2d50afe1 |
| chat_template_utils.md | 5.48 kB | | 1fe8f905 |
| chat_templates.html | 28.3 kB | | 43adda91 |
| chat_templates.md | 5.13 kB | | 012392f8 |
| clis.html | 53.4 kB | | bc2a789e |
| clis.md | 12.8 kB | | 0769d144 |
| community_tutorials.html | 31 kB | | 331e6190 |
| community_tutorials.md | 11 kB | | 3b197a53 |
| cpo_trainer.html | 144 kB | | ad582e0d |
| cpo_trainer.md | 23 kB | | 7cd05662 |
| customization.html | 31 kB | | 7f7928f1 |
| customization.md | 4.08 kB | | 6007d0d9 |
| data_utils.html | 62.7 kB | | 77834839 |
| data_utils.md | 6.87 kB | | d1599f63 |
| dataset_formats.html | 223 kB | | 728a1869 |
| dataset_formats.md | 40.2 kB | | a7257d1b |
| deepspeed_integration.html | 15.8 kB | | 180c0138 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | d56a87c0 |
| distillation_trainer.md | 12.3 kB | | 06abb3b8 |
| distributing_training.html | 96.5 kB | | ce6bb31a |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | f849a4ce |
| dpo_trainer.md | 30.8 kB | | 56edd58c |
| example_overview.html | 42.8 kB | | 1d62344b |
| example_overview.md | 19.7 kB | | 973e44c9 |
| experimental_overview.html | 10.8 kB | | 4dc06125 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | e50574e5 |
| gfpo.md | 5.24 kB | | dd11ccda |
| gkd_trainer.html | 119 kB | | e3cf865b |
| gkd_trainer.md | 14.1 kB | | df45bf9d |
| gold_trainer.html | 166 kB | | 58e44e63 |
| gold_trainer.md | 18.1 kB | | 99e3f9d3 |
| grpo_trainer.html | 560 kB | | ca461655 |
| grpo_trainer.md | 55.8 kB | | 39438dd6 |
| grpo_with_replay_buffer.html | 89.6 kB | | 1541421f |
| grpo_with_replay_buffer.md | 6.16 kB | | a5f2245f |
| gspo_token.html | 50.2 kB | | c3b3eeaa |
| gspo_token.md | 4.27 kB | | 387ab6b4 |
| index.html | 29 kB | | 728b376d |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | e26b0dc9 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 9e89e077 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | abc0bbc1 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 137 kB | | cd42c3d7 |
| kto_trainer.md | 18.4 kB | | 25f861e3 |
| liger_kernel_integration.html | 15 kB | | 8d108f7c |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 867 kB | | 82be5ae0 |
| llms.txt | 5.15 kB | | 6045c840 |
| lora_without_regret.html | 45 kB | | 66a1d70c |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 92959147 |
| merge_model_callback.md | 1.19 kB | | 30aa575f |
| minillm_trainer.html | 179 kB | | c29b4b15 |
| minillm_trainer.md | 16.4 kB | | 62167a55 |
| nash_md_trainer.html | 124 kB | | da9a6bcf |
| nash_md_trainer.md | 16.3 kB | | b79f0294 |
| nemo_gym.html | 58.5 kB | | 25fe7159 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.45 kB | | 68cd960f |
| online_dpo_trainer.html | 179 kB | | 8bd48869 |
| online_dpo_trainer.md | 23.1 kB | | 16a14419 |
| openenv.html | 114 kB | | c3de4807 |
| openenv.md | 27.8 kB | | 802bcc60 |
| orpo_trainer.html | 127 kB | | 75cd4348 |
| orpo_trainer.md | 17.7 kB | | 3d785ce4 |
| paper_index.html | 742 kB | | 200d5550 |
| paper_index.md | 19.1 kB | | 9b7452f9 |
| papo_trainer.html | 111 kB | | 237b83ce |
| papo_trainer.md | 8.82 kB | | a65d28f9 |
| peft_integration.html | 131 kB | | 0c57c62e |
| peft_integration.md | 23.9 kB | | 3cca7db4 |
| ppo_trainer.html | 278 kB | | 9dc55f05 |
| ppo_trainer.md | 41.4 kB | | f808b0fa |
| prm_trainer.html | 117 kB | | 87a05905 |
| prm_trainer.md | 13.9 kB | | 0d046f85 |
| ptt_integration.html | 29.3 kB | | b228ff32 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 050a0f00 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 95.4 kB | | f7746341 |
| rapidfire_integration.md | 17.7 kB | | 08fed5af |
| reducing_memory_usage.html | 52.4 kB | | 92f9242a |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
|