| _app | | | 185 items |
| _toctree.yml | 3.29 kB | | 4ea3f42b |
| async_grpo_trainer.html | 108 kB | | 29ff885f |
| async_grpo_trainer.md | 12.3 kB | | d0790927 |
| bco_trainer.html | 130 kB | | 32c4c107 |
| bco_trainer.md | 14.1 kB | | cce4062e |
| bema_for_reference_model.html | 90 kB | | 41fa81f8 |
| bema_for_reference_model.md | 7.18 kB | | b3d1c762 |
| callbacks.html | 95.8 kB | | 626f4ed7 |
| callbacks.md | 7.88 kB | | 68192683 |
| chat_template_utils.html | 43.9 kB | | a7c36a88 |
| chat_template_utils.md | 4.65 kB | | 257933d3 |
| clis.html | 53.4 kB | | d5b16de9 |
| clis.md | 12.8 kB | | aa82913b |
| community_tutorials.html | 31 kB | | 166b79b0 |
| community_tutorials.md | 11 kB | | 3b3405c5 |
| cpo_trainer.html | 144 kB | | 15de45e1 |
| cpo_trainer.md | 23 kB | | e834421f |
| customization.html | 31 kB | | 353e5839 |
| customization.md | 4.08 kB | | 5b71d53d |
| data_utils.html | 62.9 kB | | 52c28a04 |
| data_utils.md | 6.32 kB | | 9815a1da |
| dataset_formats.html | 223 kB | | 7964e805 |
| dataset_formats.md | 40.2 kB | | d38dd72e |
| deepspeed_integration.html | 15.8 kB | | a79e6bce |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distributing_training.html | 96.5 kB | | d43afb2c |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | 675528bb |
| dpo_trainer.md | 30.7 kB | | 923301c8 |
| example_overview.html | 43.2 kB | | 6baffc95 |
| example_overview.md | 20.1 kB | | 54ac68cf |
| experimental_overview.html | 10.8 kB | | e783d260 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | 3ddbdf4c |
| gfpo.md | 5.24 kB | | d68f031a |
| gkd_trainer.html | 119 kB | | 890dd52d |
| gkd_trainer.md | 14.1 kB | | c97adb54 |
| gold_trainer.html | 163 kB | | a865b4d5 |
| gold_trainer.md | 17.5 kB | | df02c45f |
| grpo_trainer.html | 555 kB | | e2020440 |
| grpo_trainer.md | 54 kB | | da15af79 |
| grpo_with_replay_buffer.html | 89.6 kB | | 8d403b21 |
| grpo_with_replay_buffer.md | 6.16 kB | | 6532ebd1 |
| gspo_token.html | 50.2 kB | | 1e54f408 |
| gspo_token.md | 4.27 kB | | beee5d91 |
| index.html | 29 kB | | 2ba22591 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | fe95aac3 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | ab1802b4 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| judges.html | 122 kB | | 4c2aeb69 |
| judges.md | 15.8 kB | | 3fe4aa5f |
| kernels_hub.html | 26.8 kB | | 44b1c958 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 138 kB | | f5ff94e4 |
| kto_trainer.md | 19.4 kB | | 03f8e815 |
| liger_kernel_integration.html | 15 kB | | a0cbce0e |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 833 kB | | b15b7a00 |
| llms.txt | 5.04 kB | | 6bd8f3c7 |
| lora_without_regret.html | 45 kB | | 96359042 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 79205408 |
| merge_model_callback.md | 1.19 kB | | 4e71c010 |
| minillm_trainer.html | 179 kB | | 76b1c3b3 |
| minillm_trainer.md | 16.4 kB | | c5111b0a |
| nash_md_trainer.html | 130 kB | | b35d77f8 |
| nash_md_trainer.md | 17.1 kB | | b9ab38ff |
| nemo_gym.html | 58.5 kB | | 368a1542 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.45 kB | | 74d0516b |
| online_dpo_trainer.html | 195 kB | | 4cfdad95 |
| online_dpo_trainer.md | 26.3 kB | | 1ac62423 |
| openenv.html | 114 kB | | c64a616e |
| openenv.md | 27.8 kB | | 8ba9db0d |
| orpo_trainer.html | 127 kB | | 4b490649 |
| orpo_trainer.md | 17.7 kB | | 1cf10ae5 |
| paper_index.html | 732 kB | | 936eb0d3 |
| paper_index.md | 17 kB | | 6bc1e92a |
| papo_trainer.html | 111 kB | | 1188022c |
| papo_trainer.md | 8.82 kB | | f7790e40 |
| peft_integration.html | 131 kB | | 7799f539 |
| peft_integration.md | 23.9 kB | | 5ed7037e |
| ppo_trainer.html | 280 kB | | 10a84362 |
| ppo_trainer.md | 42 kB | | 1c034697 |
| prm_trainer.html | 117 kB | | 223c98de |
| prm_trainer.md | 13.9 kB | | c81ff2d1 |
| ptt_integration.html | 29.3 kB | | 8976d23c |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | eb42cf53 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | 67babbca |
| rapidfire_integration.md | 12.8 kB | | c14e6d99 |
| reducing_memory_usage.html | 52.4 kB | | 0f285e8b |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
| reward_trainer.html | 175 kB | | 0f07b1b6 |
| reward_trainer.md | 21.5 kB | | 22721c37 |
|