| _app | | | 251 items |
| _toctree.yml | 3.38 kB | | 9da8f3eb |
| async_grpo_trainer.html | 108 kB | | bf23608e |
| async_grpo_trainer.md | 12.3 kB | | 97b9536a |
| bco_trainer.html | 130 kB | | 46beb72c |
| bco_trainer.md | 14.1 kB | | 5b77976f |
| bema_for_reference_model.html | 90 kB | | cddecc62 |
| bema_for_reference_model.md | 7.18 kB | | 0ddc09ef |
| callbacks.html | 95.8 kB | | 0e167399 |
| callbacks.md | 7.88 kB | | 537dde1a |
| chat_template_utils.html | 46.2 kB | | a3d75425 |
| chat_template_utils.md | 5.77 kB | | 7c26c665 |
| chat_templates.html | 35.4 kB | | 52763bcc |
| chat_templates.md | 6.48 kB | | 0ed7a82d |
| clis.html | 53.4 kB | | dbd0efc9 |
| clis.md | 12.8 kB | | 96ecf9c4 |
| community_tutorials.html | 31 kB | | d2e08505 |
| community_tutorials.md | 10.9 kB | | 42d913a7 |
| cpo_trainer.html | 144 kB | | bc306415 |
| cpo_trainer.md | 23 kB | | 42d9dc71 |
| customization.html | 30.9 kB | | 873415d7 |
| customization.md | 4.04 kB | | d32ad74f |
| data_utils.html | 62.7 kB | | 4a36329d |
| data_utils.md | 6.87 kB | | 6fe976ba |
| dataset_formats.html | 223 kB | | dff1ae35 |
| dataset_formats.md | 40.1 kB | | f247c51e |
| deepspeed_integration.html | 15.8 kB | | fc5750e4 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 161 kB | | 6f51da82 |
| distillation_trainer.md | 12.3 kB | | a8cfb800 |
| distributing_training.html | 96.5 kB | | 339c9623 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | acec8983 |
| dpo_trainer.md | 30.7 kB | | f5455254 |
| example_overview.html | 42.7 kB | | cb806116 |
| example_overview.md | 19.6 kB | | a72bec48 |
| experimental_overview.html | 10.8 kB | | 2b7ec283 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 85 kB | | 1206d6ce |
| gfpo.md | 5.24 kB | | 79fb6e49 |
| gkd_trainer.html | 119 kB | | 4f1a169a |
| gkd_trainer.md | 14.1 kB | | 4aff4a0c |
| gold_trainer.html | 166 kB | | 1ac403ab |
| gold_trainer.md | 18.1 kB | | 6a0e7984 |
| grpo_trainer.html | 561 kB | | bba14880 |
| grpo_trainer.md | 55.9 kB | | 9d5c15e4 |
| grpo_with_replay_buffer.html | 90.3 kB | | d897d3d4 |
| grpo_with_replay_buffer.md | 6.16 kB | | f6ed4aa7 |
| gspo_token.html | 50.2 kB | | 152f8716 |
| gspo_token.md | 4.27 kB | | 1ff0c2df |
| index.html | 29 kB | | 7d85013e |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 129f42c9 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 8e67c5b0 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | 4a6cc628 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 134 kB | | f411b60f |
| kto_trainer.md | 18 kB | | 00ce271d |
| liger_kernel_integration.html | 15 kB | | f66aed0f |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 870 kB | | 1f7ddf12 |
| llms.txt | 5.15 kB | | 005b36a9 |
| lora_without_regret.html | 45 kB | | 3f189e72 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 24ded41b |
| merge_model_callback.md | 1.19 kB | | ff35b0d4 |
| minillm_trainer.html | 180 kB | | c02bc889 |
| minillm_trainer.md | 16.4 kB | | b94033f0 |
| nash_md_trainer.html | 125 kB | | 0366c5c4 |
| nash_md_trainer.md | 16.3 kB | | 16aa8dfe |
| nemo_gym.html | 58.5 kB | | e108c9d0 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.44 kB | | 441c8550 |
| online_dpo_trainer.html | 180 kB | | 881fe79d |
| online_dpo_trainer.md | 23.1 kB | | 5069daab |
| openenv.html | 114 kB | | 6a83a614 |
| openenv.md | 27.8 kB | | 2c6660e9 |
| orpo_trainer.html | 127 kB | | fadbb6e0 |
| orpo_trainer.md | 17.7 kB | | 01f0ab01 |
| paper_index.html | 742 kB | | 1717c49a |
| paper_index.md | 19.1 kB | | 78e171c5 |
| papo_trainer.html | 112 kB | | 5bf94616 |
| papo_trainer.md | 8.82 kB | | dab9619e |
| peft_integration.html | 131 kB | | 890f5419 |
| peft_integration.md | 23.9 kB | | 9e01ce0b |
| ppo_trainer.html | 279 kB | | 1546d72d |
| ppo_trainer.md | 41.4 kB | | 95d64d51 |
| prm_trainer.html | 118 kB | | 5a33415d |
| prm_trainer.md | 13.9 kB | | 7e48c4bf |
| ptt_integration.html | 29.3 kB | | a34c7507 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | b659f428 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 95.4 kB | | c88d18a4 |
| rapidfire_integration.md | 17.7 kB | | 08fed5af |
| reducing_memory_usage.html | 57 kB | | 870f6157 |
| reducing_memory_usage.md | 13.7 kB | | 60dcf4aa |
|