| _app | | | 378 items |
| _toctree.yml | 3.43 kB | | 4aa162d5 |
| async_grpo_trainer.html | 108 kB | | 178d19f9 |
| async_grpo_trainer.md | 12.3 kB | | 0ff7e6ea |
| bco_trainer.html | 131 kB | | 15f480c3 |
| bco_trainer.md | 14.2 kB | | 39f09509 |
| bema_for_reference_model.html | 90 kB | | d2e439f5 |
| bema_for_reference_model.md | 7.18 kB | | e211d6db |
| callbacks.html | 95.8 kB | | 86a6f43c |
| callbacks.md | 7.88 kB | | 83e9bede |
| chat_template_utils.html | 46.7 kB | | 0ebe3045 |
| chat_template_utils.md | 5.88 kB | | e856b1da |
| chat_templates.html | 46.4 kB | | 811b4920 |
| chat_templates.md | 9.03 kB | | bd306b14 |
| clis.html | 53.6 kB | | 30c02bcc |
| clis.md | 12.8 kB | | 6edbdd41 |
| community_tutorials.html | 31 kB | | 22976129 |
| community_tutorials.md | 11 kB | | 10cde4c8 |
| cpo_trainer.html | 145 kB | | b93416da |
| cpo_trainer.md | 23.2 kB | | 27f8f499 |
| customization.html | 31.1 kB | | 81e06761 |
| customization.md | 4.08 kB | | b1385a55 |
| data_utils.html | 62.8 kB | | 93519a56 |
| data_utils.md | 6.87 kB | | 4485646e |
| dataset_formats.html | 224 kB | | 389efcbd |
| dataset_formats.md | 43 kB | | a7035365 |
| deepspeed_integration.html | 15.9 kB | | a0b98a15 |
| deepspeed_integration.md | 1.52 kB | | e5b0fad5 |
| distillation_trainer.html | 161 kB | | da5e2065 |
| distillation_trainer.md | 12.3 kB | | 7aa96263 |
| distributing_training.html | 96.7 kB | | 6ced3b90 |
| distributing_training.md | 21 kB | | 4e11b37d |
| dpo_trainer.html | 233 kB | | 699fa0b5 |
| dpo_trainer.md | 31.1 kB | | 59f7b73b |
| example_overview.html | 43.3 kB | | ecd5cc33 |
| example_overview.md | 20.1 kB | | b9094e30 |
| experimental_overview.html | 10.8 kB | | 5a404fa8 |
| experimental_overview.md | 1.62 kB | | 45d90cc6 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 85.1 kB | | 9860dd89 |
| gfpo.md | 5.24 kB | | 14596e1d |
| gkd_trainer.html | 119 kB | | 90873d1b |
| gkd_trainer.md | 14.1 kB | | cfb1afc5 |
| gold_trainer.html | 166 kB | | ba93191a |
| gold_trainer.md | 18.1 kB | | 15570e20 |
| grpo_trainer.html | 562 kB | | d8585c2b |
| grpo_trainer.md | 61.8 kB | | 97d00cf5 |
| grpo_with_replay_buffer.html | 90.3 kB | | 37a3022f |
| grpo_with_replay_buffer.md | 6.16 kB | | e72177cc |
| gspo_token.html | 50.2 kB | | 92acea1f |
| gspo_token.md | 4.27 kB | | cce0215e |
| index.html | 29 kB | | b92d5622 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 455a6481 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 33.1 kB | | 67b0a130 |
| jobs_training.md | 6.46 kB | | cb814663 |
| kernels_hub.html | 26.9 kB | | f2f06fb9 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 134 kB | | 89e688a0 |
| kto_trainer.md | 18.2 kB | | c3876189 |
| liger_kernel_integration.html | 15 kB | | 64fadad5 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 963 kB | | b726d974 |
| llms.txt | 5.27 kB | | ee0a03c7 |
| lora_without_regret.html | 45.1 kB | | e9417277 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 6a669e4d |
| merge_model_callback.md | 1.19 kB | | e1b6e630 |
| minillm_trainer.html | 180 kB | | fb6a93df |
| minillm_trainer.md | 16.4 kB | | 2c26496e |
| nash_md_trainer.html | 125 kB | | 5fe05a3f |
| nash_md_trainer.md | 16.6 kB | | c9e7b837 |
| nemo_gym.html | 58.7 kB | | 468741ec |
| nemo_gym.md | 10.3 kB | | 45caccd9 |
| objects.inv | 2.47 kB | | 6a63b95d |
| online_dpo_trainer.html | 180 kB | | b2eebe4d |
| online_dpo_trainer.md | 23.3 kB | | 0f3789c9 |
| openenv.html | 114 kB | | d63463d1 |
| openenv.md | 27.8 kB | | e612a3c2 |
| openreward.html | 67.4 kB | | a9b06ab3 |
| openreward.md | 10.6 kB | | 6c81ea4e |
| orpo_trainer.html | 128 kB | | e706289b |
| orpo_trainer.md | 17.9 kB | | 5de70fd8 |
| paper_index.html | 763 kB | | 6aac52e7 |
| paper_index.md | 85.1 kB | | cd701aea |
| papo_trainer.html | 112 kB | | 99ad33bb |
| papo_trainer.md | 8.82 kB | | 0527aa2b |
| peft_integration.html | 131 kB | | 59eecdd5 |
| peft_integration.md | 23.9 kB | | 389101cb |
| ppo_trainer.html | 279 kB | | 2f6964ce |
| ppo_trainer.md | 41.5 kB | | e00802cd |
| prm_trainer.html | 118 kB | | 73137358 |
| prm_trainer.md | 14.2 kB | | 723c030f |
| ptt_integration.html | 29.3 kB | | 187dfaa0 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.7 kB | | a56905d5 |
| quickstart.md | 3.62 kB | | 5adf1d8b |
| rapidfire_integration.html | 95.6 kB | | 14608418 |
| rapidfire_integration.md | 17.8 kB | | 4f58dc65 |
|