| _app | | | 137 items |
| _toctree.yml | 3.38 kB | | 9da8f3eb |
| async_grpo_trainer.html | 108 kB | | 885a1c04 |
| async_grpo_trainer.md | 12.3 kB | | 753dfb82 |
| bco_trainer.html | 130 kB | | beeaf251 |
| bco_trainer.md | 14.1 kB | | e7a48bd9 |
| bema_for_reference_model.html | 90 kB | | dd78bb3e |
| bema_for_reference_model.md | 7.18 kB | | 7aac0a50 |
| callbacks.html | 95.8 kB | | a025e2f3 |
| callbacks.md | 7.88 kB | | 3c2df48b |
| chat_template_utils.html | 45.8 kB | | bf82d48a |
| chat_template_utils.md | 5.48 kB | | 02ff7878 |
| chat_templates.html | 28.3 kB | | fc031dda |
| chat_templates.md | 5.13 kB | | 40f43b10 |
| clis.html | 53.4 kB | | 25162847 |
| clis.md | 12.8 kB | | 5f9ee25f |
| community_tutorials.html | 31 kB | | ab62dfb0 |
| community_tutorials.md | 11 kB | | a55680f6 |
| cpo_trainer.html | 144 kB | | b4dad6c1 |
| cpo_trainer.md | 23 kB | | 15a7faa8 |
| customization.html | 31 kB | | e8bfe075 |
| customization.md | 4.08 kB | | 5a84b9e8 |
| data_utils.html | 62.7 kB | | 841db7e3 |
| data_utils.md | 6.87 kB | | 1b21f5d4 |
| dataset_formats.html | 223 kB | | 08278541 |
| dataset_formats.md | 40.2 kB | | deab9ecc |
| deepspeed_integration.html | 15.8 kB | | d1799241 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | 88813181 |
| distillation_trainer.md | 12.3 kB | | aaf46eb0 |
| distributing_training.html | 96.5 kB | | 9b5746dd |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | b8c2a786 |
| dpo_trainer.md | 30.8 kB | | 49320d3b |
| example_overview.html | 42.8 kB | | 38afa307 |
| example_overview.md | 19.7 kB | | b58b76ea |
| experimental_overview.html | 10.8 kB | | 15cb039e |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | 7fc1ab4d |
| gfpo.md | 5.24 kB | | d443a181 |
| gkd_trainer.html | 119 kB | | e2607b3f |
| gkd_trainer.md | 14.1 kB | | 43354d1a |
| gold_trainer.html | 166 kB | | c34d69a1 |
| gold_trainer.md | 18.1 kB | | 75cdab17 |
| grpo_trainer.html | 560 kB | | d69734f6 |
| grpo_trainer.md | 55.8 kB | | a51139d8 |
| grpo_with_replay_buffer.html | 89.6 kB | | c936f2f2 |
| grpo_with_replay_buffer.md | 6.16 kB | | 3f1d0bf5 |
| gspo_token.html | 50.2 kB | | 58525c24 |
| gspo_token.md | 4.27 kB | | 4aa39892 |
| index.html | 29 kB | | ccba1f04 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | dc8d32c4 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | c601c830 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | 6fa8d85c |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 137 kB | | 7a52de74 |
| kto_trainer.md | 18.4 kB | | 371a2933 |
| liger_kernel_integration.html | 15 kB | | 5b669f9c |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 862 kB | | e0f7d1fb |
| llms.txt | 5.15 kB | | de2de41d |
| lora_without_regret.html | 45 kB | | 2c540ebe |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | cdc9383c |
| merge_model_callback.md | 1.19 kB | | fe93ce17 |
| minillm_trainer.html | 179 kB | | f536233f |
| minillm_trainer.md | 16.4 kB | | 3518ea35 |
| nash_md_trainer.html | 124 kB | | 6af743b0 |
| nash_md_trainer.md | 16.3 kB | | d4e9abc4 |
| nemo_gym.html | 58.5 kB | | e392b492 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.45 kB | | 32bea30a |
| online_dpo_trainer.html | 179 kB | | 2f3b164c |
| online_dpo_trainer.md | 23.1 kB | | 409c9bb2 |
| openenv.html | 114 kB | | 2fd544d5 |
| openenv.md | 27.8 kB | | f762106b |
| orpo_trainer.html | 127 kB | | f1a29380 |
| orpo_trainer.md | 17.7 kB | | da69ec80 |
| paper_index.html | 742 kB | | dd0596bf |
| paper_index.md | 19.1 kB | | 3acacbd1 |
| papo_trainer.html | 111 kB | | eed2c50b |
| papo_trainer.md | 8.82 kB | | 0ba4bdc7 |
| peft_integration.html | 131 kB | | 1fd4b7f1 |
| peft_integration.md | 23.9 kB | | 9ef65f83 |
| ppo_trainer.html | 278 kB | | 007ea87a |
| ppo_trainer.md | 41.4 kB | | 720fa865 |
| prm_trainer.html | 117 kB | | 7aa72565 |
| prm_trainer.md | 13.9 kB | | ecb05ef5 |
| ptt_integration.html | 29.3 kB | | 4a921c7a |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 26882b81 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | 66b3b89a |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | 3d24df1e |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
|