| _app | | | 236 items |
| _toctree.yml | 3.35 kB | | ac839051 |
| async_grpo_trainer.html | 108 kB | | da2b7161 |
| async_grpo_trainer.md | 12.3 kB | | fa4b8068 |
| bco_trainer.html | 130 kB | | 313ca5bb |
| bco_trainer.md | 14.1 kB | | 0ffa53d1 |
| bema_for_reference_model.html | 90 kB | | 196adf99 |
| bema_for_reference_model.md | 7.18 kB | | 3f348286 |
| callbacks.html | 95.8 kB | | ddb77300 |
| callbacks.md | 7.88 kB | | 099ed4f4 |
| chat_template_utils.html | 45.8 kB | | 365f613c |
| chat_template_utils.md | 5.48 kB | | ab3151bf |
| chat_templates.html | 28.3 kB | | 3690266a |
| chat_templates.md | 5.13 kB | | 81b75764 |
| clis.html | 53.4 kB | | 11a3e004 |
| clis.md | 12.8 kB | | db07946e |
| community_tutorials.html | 31 kB | | 36a50a32 |
| community_tutorials.md | 11 kB | | 1ede2f05 |
| cpo_trainer.html | 144 kB | | e71cce24 |
| cpo_trainer.md | 23 kB | | ff00b008 |
| customization.html | 31 kB | | a2d020af |
| customization.md | 4.08 kB | | e35b8043 |
| data_utils.html | 62.9 kB | | 660018d9 |
| data_utils.md | 6.32 kB | | 47f29775 |
| dataset_formats.html | 223 kB | | dd6b5148 |
| dataset_formats.md | 40.2 kB | | c95c0582 |
| deepspeed_integration.html | 15.8 kB | | fe162ffc |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | 8e089a09 |
| distillation_trainer.md | 12.3 kB | | 2921b01f |
| distributing_training.html | 96.5 kB | | fb34d163 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | 895f4a3b |
| dpo_trainer.md | 30.8 kB | | 95b8297d |
| example_overview.html | 42.8 kB | | fc0a7525 |
| example_overview.md | 19.7 kB | | b18e5b1c |
| experimental_overview.html | 10.8 kB | | bd5f9e37 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | 80aa326c |
| gfpo.md | 5.24 kB | | 8f836397 |
| gkd_trainer.html | 119 kB | | 5a1bb8c8 |
| gkd_trainer.md | 14.1 kB | | ffb7a6fc |
| gold_trainer.html | 166 kB | | c32e1e9a |
| gold_trainer.md | 18.1 kB | | 7c9df577 |
| grpo_trainer.html | 560 kB | | 5eb7cea1 |
| grpo_trainer.md | 55.8 kB | | 1c60829f |
| grpo_with_replay_buffer.html | 89.6 kB | | 0817831d |
| grpo_with_replay_buffer.md | 6.16 kB | | 5c67fe83 |
| gspo_token.html | 50.2 kB | | bd23614d |
| gspo_token.md | 4.27 kB | | 5a723188 |
| index.html | 29 kB | | 17025992 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | cb036430 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 293562e9 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | 7a69f742 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 137 kB | | 4ac8e3c3 |
| kto_trainer.md | 18.1 kB | | 435ae863 |
| liger_kernel_integration.html | 15 kB | | 021bba59 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 842 kB | | ff056f6c |
| llms.txt | 5.08 kB | | 5b04522f |
| lora_without_regret.html | 45 kB | | 7de468ff |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 7e7e0655 |
| merge_model_callback.md | 1.19 kB | | 86f6b5a9 |
| minillm_trainer.html | 179 kB | | 98e6ce71 |
| minillm_trainer.md | 16.4 kB | | 6c0d830a |
| nash_md_trainer.html | 124 kB | | 15e1e3cf |
| nash_md_trainer.md | 16.3 kB | | 0b173706 |
| nemo_gym.html | 58.5 kB | | e6d5bf9f |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.41 kB | | 21e855f8 |
| online_dpo_trainer.html | 179 kB | | fc613329 |
| online_dpo_trainer.md | 23.1 kB | | 04a915df |
| openenv.html | 114 kB | | 516dac3d |
| openenv.md | 27.8 kB | | 8fdd9dc4 |
| orpo_trainer.html | 127 kB | | e31bc6e0 |
| orpo_trainer.md | 17.7 kB | | 559bd659 |
| paper_index.html | 734 kB | | 50ebb27f |
| paper_index.md | 19.1 kB | | ffd1dcbe |
| papo_trainer.html | 111 kB | | a72b5d16 |
| papo_trainer.md | 8.82 kB | | d6e1d13c |
| peft_integration.html | 131 kB | | dc6010e2 |
| peft_integration.md | 23.9 kB | | 947af9d1 |
| ppo_trainer.html | 278 kB | | b315a699 |
| ppo_trainer.md | 41.4 kB | | b0768695 |
| prm_trainer.html | 117 kB | | 991cc825 |
| prm_trainer.md | 13.9 kB | | 8b1416a8 |
| ptt_integration.html | 29.3 kB | | 480dc308 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 3a165e5b |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | 1bcb1071 |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | 26763cba |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
|