| _app | | | 440 items |
| _toctree.yml | 3.38 kB | | 9da8f3eb |
| async_grpo_trainer.html | 108 kB | | 1b7c544d |
| async_grpo_trainer.md | 12.3 kB | | f7004854 |
| bco_trainer.html | 130 kB | | a7dd6afb |
| bco_trainer.md | 14.1 kB | | 0765f580 |
| bema_for_reference_model.html | 90 kB | | 674c885d |
| bema_for_reference_model.md | 7.18 kB | | 3888e11e |
| callbacks.html | 95.8 kB | | 92c28f1b |
| callbacks.md | 7.88 kB | | a9313688 |
| chat_template_utils.html | 46.2 kB | | 2f58cc56 |
| chat_template_utils.md | 5.76 kB | | 45026eeb |
| chat_templates.html | 33.5 kB | | 631014ff |
| chat_templates.md | 6.03 kB | | a3579911 |
| clis.html | 53.4 kB | | 4467ccc6 |
| clis.md | 12.8 kB | | 54b6a573 |
| community_tutorials.html | 31 kB | | 23660e0e |
| community_tutorials.md | 11 kB | | 2f18f9ed |
| cpo_trainer.html | 144 kB | | 3fc96bfe |
| cpo_trainer.md | 23 kB | | cfc70d72 |
| customization.html | 31 kB | | e2580a95 |
| customization.md | 4.08 kB | | 58148487 |
| data_utils.html | 62.7 kB | | 694f24a5 |
| data_utils.md | 6.87 kB | | 0ec29f18 |
| dataset_formats.html | 223 kB | | dfdeac9e |
| dataset_formats.md | 40.2 kB | | 2ea50b05 |
| deepspeed_integration.html | 15.8 kB | | 685c5eb4 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 161 kB | | 741b8ae7 |
| distillation_trainer.md | 12.3 kB | | f596029b |
| distributing_training.html | 96.5 kB | | 02ede9eb |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 233 kB | | a3e74a89 |
| dpo_trainer.md | 30.8 kB | | 4db0f515 |
| example_overview.html | 42.8 kB | | 4ae7fa07 |
| example_overview.md | 19.7 kB | | a11fbf67 |
| experimental_overview.html | 10.8 kB | | 93a6574e |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 85 kB | | db02db06 |
| gfpo.md | 5.24 kB | | b4b4ad92 |
| gkd_trainer.html | 119 kB | | 1339df3f |
| gkd_trainer.md | 14.1 kB | | 3a1308d8 |
| gold_trainer.html | 166 kB | | a5f17808 |
| gold_trainer.md | 18.1 kB | | 334b55d0 |
| grpo_trainer.html | 561 kB | | 61eec9fa |
| grpo_trainer.md | 55.8 kB | | eccbb55a |
| grpo_with_replay_buffer.html | 90.3 kB | | 71af8eb9 |
| grpo_with_replay_buffer.md | 6.16 kB | | 596ae210 |
| gspo_token.html | 50.2 kB | | d00a4cfd |
| gspo_token.md | 4.27 kB | | 28862040 |
| index.html | 29 kB | | 66c73927 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 6e175aa4 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 26320794 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| judges.html | 122 kB | | 39ead7e1 |
| judges.md | 15.8 kB | | bc8f936b |
| kernels_hub.html | 26.8 kB | | f33d941f |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 138 kB | | ee969572 |
| kto_trainer.md | 18.3 kB | | e27b0bc8 |
| liger_kernel_integration.html | 15 kB | | fe109f45 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 868 kB | | 94977469 |
| llms.txt | 5.15 kB | | a5b51fa7 |
| lora_without_regret.html | 45 kB | | aab4eca2 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 1c1cc011 |
| merge_model_callback.md | 1.19 kB | | 1acb9c2b |
| minillm_trainer.html | 180 kB | | df54bb17 |
| minillm_trainer.md | 16.4 kB | | 32d9ebc7 |
| nash_md_trainer.html | 125 kB | | 618c9597 |
| nash_md_trainer.md | 16.3 kB | | 2e8ac197 |
| nemo_gym.html | 58.5 kB | | b6702a55 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.45 kB | | d24c3a1d |
| online_dpo_trainer.html | 180 kB | | 246e2012 |
| online_dpo_trainer.md | 23.1 kB | | 813dd7f1 |
| openenv.html | 114 kB | | 842d1234 |
| openenv.md | 27.8 kB | | cbc7e186 |
| orpo_trainer.html | 127 kB | | 6751c857 |
| orpo_trainer.md | 17.7 kB | | 0e8bb135 |
| paper_index.html | 742 kB | | 15a45144 |
| paper_index.md | 19.1 kB | | 37b04bcc |
| papo_trainer.html | 112 kB | | 8027b84e |
| papo_trainer.md | 8.82 kB | | e7157c54 |
| peft_integration.html | 131 kB | | 5e4b8043 |
| peft_integration.md | 23.9 kB | | 3812a8e7 |
| ppo_trainer.html | 279 kB | | d4d2814f |
| ppo_trainer.md | 41.4 kB | | 36669c17 |
| prm_trainer.html | 118 kB | | 204a1d3c |
| prm_trainer.md | 13.9 kB | | aaaf8e1d |
| ptt_integration.html | 29.3 kB | | d10f67f8 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 25726e5e |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 95.4 kB | | 928be4d0 |
| rapidfire_integration.md | 17.7 kB | | 08fed5af |
|