| _app | | | 206 items |
| _toctree.yml | 3.38 kB | | 9da8f3eb |
| async_grpo_trainer.html | 108 kB | | dc46c840 |
| async_grpo_trainer.md | 12.3 kB | | fa540406 |
| bco_trainer.html | 130 kB | | 5ef6dc8d |
| bco_trainer.md | 14.2 kB | | b4068b93 |
| bema_for_reference_model.html | 90 kB | | 012f1da0 |
| bema_for_reference_model.md | 7.18 kB | | d02cf762 |
| callbacks.html | 95.8 kB | | 729dbe97 |
| callbacks.md | 7.88 kB | | 57825116 |
| chat_template_utils.html | 46.2 kB | | 0893310d |
| chat_template_utils.md | 5.78 kB | | a5566702 |
| chat_templates.html | 37.1 kB | | bd9f5666 |
| chat_templates.md | 7.04 kB | | b07ef723 |
| clis.html | 53.4 kB | | 19487ed1 |
| clis.md | 12.8 kB | | d4a33107 |
| community_tutorials.html | 31 kB | | f05a033b |
| community_tutorials.md | 11 kB | | 633c4d7b |
| cpo_trainer.html | 145 kB | | 17ec642d |
| cpo_trainer.md | 23.2 kB | | a4b919d4 |
| customization.html | 31 kB | | 15f045a6 |
| customization.md | 4.08 kB | | 4d9861ba |
| data_utils.html | 62.7 kB | | 5a930052 |
| data_utils.md | 6.87 kB | | 8f5c716e |
| dataset_formats.html | 223 kB | | a8b36f9f |
| dataset_formats.md | 43 kB | | 80768ed8 |
| deepspeed_integration.html | 15.8 kB | | b25db882 |
| deepspeed_integration.md | 1.52 kB | | e5b0fad5 |
| distillation_trainer.html | 161 kB | | 3f2eb6b8 |
| distillation_trainer.md | 12.3 kB | | e8ba4cf4 |
| distributing_training.html | 96.5 kB | | 5347f30e |
| distributing_training.md | 21 kB | | 75949925 |
| dpo_trainer.html | 233 kB | | ae4316e4 |
| dpo_trainer.md | 30.9 kB | | 2842ab2c |
| example_overview.html | 42.7 kB | | 65217fb4 |
| example_overview.md | 19.7 kB | | e3be7f64 |
| experimental_overview.html | 10.8 kB | | c9a71f10 |
| experimental_overview.md | 1.62 kB | | 45d90cc6 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 85 kB | | 8ef9a1d8 |
| gfpo.md | 5.24 kB | | 3d05c1ec |
| gkd_trainer.html | 119 kB | | 46779b0c |
| gkd_trainer.md | 14.1 kB | | de29734d |
| gold_trainer.html | 166 kB | | 2a813bad |
| gold_trainer.md | 18.1 kB | | 1330b4b8 |
| grpo_trainer.html | 561 kB | | 0a91599e |
| grpo_trainer.md | 61.5 kB | | 56467208 |
| grpo_with_replay_buffer.html | 90.3 kB | | eaffb804 |
| grpo_with_replay_buffer.md | 6.16 kB | | ba287d0e |
| gspo_token.html | 50.2 kB | | 3ed3f974 |
| gspo_token.md | 4.27 kB | | f21dff9d |
| index.html | 29 kB | | 23a08a74 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | d801a2d0 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 4c50a639 |
| jobs_training.md | 6.46 kB | | cb814663 |
| kernels_hub.html | 26.8 kB | | 3f782855 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 134 kB | | 1e3ca759 |
| kto_trainer.md | 18.2 kB | | 58d606e1 |
| liger_kernel_integration.html | 15 kB | | 020b530c |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 947 kB | | 283b77df |
| llms.txt | 5.15 kB | | b8b92924 |
| lora_without_regret.html | 45 kB | | 63d8a189 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | df09de4d |
| merge_model_callback.md | 1.19 kB | | 4c552536 |
| minillm_trainer.html | 180 kB | | b3fa1782 |
| minillm_trainer.md | 16.4 kB | | 19d0f46d |
| nash_md_trainer.html | 125 kB | | caf8e5ea |
| nash_md_trainer.md | 16.6 kB | | 98868797 |
| nemo_gym.html | 58.5 kB | | f4fac1aa |
| nemo_gym.md | 10.3 kB | | 45caccd9 |
| objects.inv | 2.45 kB | | 0c363f29 |
| online_dpo_trainer.html | 180 kB | | 5cdc0470 |
| online_dpo_trainer.md | 23.3 kB | | 049eb3a7 |
| openenv.html | 114 kB | | 23937c9f |
| openenv.md | 27.8 kB | | f5adb47c |
| orpo_trainer.html | 128 kB | | fdadc2cf |
| orpo_trainer.md | 17.9 kB | | be49d55d |
| paper_index.html | 742 kB | | 5da1fda4 |
| paper_index.md | 84 kB | | 003203b6 |
| papo_trainer.html | 112 kB | | 07f445e7 |
| papo_trainer.md | 8.82 kB | | c668b7eb |
| peft_integration.html | 131 kB | | 629f1e52 |
| peft_integration.md | 23.9 kB | | a48bc88f |
| ppo_trainer.html | 279 kB | | e3700df0 |
| ppo_trainer.md | 41.5 kB | | 67944b9f |
| prm_trainer.html | 118 kB | | dc021d31 |
| prm_trainer.md | 14.2 kB | | 65bf31e0 |
| ptt_integration.html | 29.3 kB | | a202ab18 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 5de34e87 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 95.4 kB | | aa086fb7 |
| rapidfire_integration.md | 17.8 kB | | b0dd6d2b |
| reducing_memory_usage.html | 57 kB | | 6b85e56b |
| reducing_memory_usage.md | 13.7 kB | | 7b69a2ce |
|