| _app | | | 135 items |
| _toctree.yml | 3.29 kB | | 3ae9d845 |
| async_grpo_trainer.html | 108 kB | | 5097510f |
| async_grpo_trainer.md | 12.3 kB | | 85a415a2 |
| bco_trainer.html | 130 kB | | d5fc8892 |
| bco_trainer.md | 14.1 kB | | aac25fef |
| bema_for_reference_model.html | 90 kB | | 26c2976f |
| bema_for_reference_model.md | 7.18 kB | | 5cf4877d |
| callbacks.html | 95.8 kB | | 0d3dfda7 |
| callbacks.md | 7.88 kB | | 399b1d7f |
| chat_template_utils.html | 45.5 kB | | 4311dd60 |
| chat_template_utils.md | 5.3 kB | | 0eb2154d |
| clis.html | 53.4 kB | | 1e9711bd |
| clis.md | 12.8 kB | | 61c6a9ac |
| community_tutorials.html | 31 kB | | abb939bb |
| community_tutorials.md | 11 kB | | b9cf975e |
| cpo_trainer.html | 144 kB | | 4bfb2bdb |
| cpo_trainer.md | 23 kB | | 0c075bd1 |
| customization.html | 31 kB | | 66a89e4b |
| customization.md | 4.08 kB | | 1d63a45d |
| data_utils.html | 62.9 kB | | 8840cdee |
| data_utils.md | 6.32 kB | | 7991d593 |
| dataset_formats.html | 223 kB | | 4a8d23fc |
| dataset_formats.md | 40.2 kB | | c1a1eaeb |
| deepspeed_integration.html | 15.8 kB | | 0446b0da |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | 399f4daf |
| distillation_trainer.md | 12.3 kB | | 38422ffb |
| distributing_training.html | 96.5 kB | | e9468aa6 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | 37152575 |
| dpo_trainer.md | 30.8 kB | | 897b0a31 |
| example_overview.html | 42.7 kB | | 0d4b309b |
| example_overview.md | 19.7 kB | | e251a207 |
| experimental_overview.html | 10.8 kB | | e8056cb3 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | 38e83c20 |
| gfpo.md | 5.24 kB | | a1afd9af |
| gkd_trainer.html | 119 kB | | 6f31edc4 |
| gkd_trainer.md | 14.1 kB | | 6149064d |
| gold_trainer.html | 166 kB | | b38b5e3f |
| gold_trainer.md | 18.1 kB | | c26f3967 |
| grpo_trainer.html | 560 kB | | 3412a629 |
| grpo_trainer.md | 55.4 kB | | e0a62554 |
| grpo_with_replay_buffer.html | 89.6 kB | | c676d3dd |
| grpo_with_replay_buffer.md | 6.16 kB | | 3d9951ba |
| gspo_token.html | 50.2 kB | | 7a12b872 |
| gspo_token.md | 4.27 kB | | d571b318 |
| index.html | 29 kB | | 7e4c2d77 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | a32f7b09 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 7e0a274c |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | 1a02523e |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 137 kB | | 7686a649 |
| kto_trainer.md | 18.1 kB | | efc9962d |
| liger_kernel_integration.html | 15 kB | | 01ff2281 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 836 kB | | 3868bc08 |
| llms.txt | 5 kB | | c323c4b3 |
| lora_without_regret.html | 45 kB | | 4334c5ba |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | d3800436 |
| merge_model_callback.md | 1.19 kB | | a45abc17 |
| minillm_trainer.html | 179 kB | | df4f848d |
| minillm_trainer.md | 16.4 kB | | 9b3b06f9 |
| nash_md_trainer.html | 124 kB | | b33e429f |
| nash_md_trainer.md | 16.3 kB | | b1966d85 |
| nemo_gym.html | 58.5 kB | | d9c79c78 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.41 kB | | 67d28edb |
| online_dpo_trainer.html | 179 kB | | 5d35f981 |
| online_dpo_trainer.md | 23.1 kB | | 6abe1ca2 |
| openenv.html | 114 kB | | cb7caf75 |
| openenv.md | 27.8 kB | | 74ca4007 |
| orpo_trainer.html | 127 kB | | 08001086 |
| orpo_trainer.md | 17.7 kB | | c0c215db |
| paper_index.html | 734 kB | | 663d5605 |
| paper_index.md | 19.1 kB | | 4fb13f99 |
| papo_trainer.html | 111 kB | | ce3fd645 |
| papo_trainer.md | 8.82 kB | | a5551989 |
| peft_integration.html | 131 kB | | aefb36a6 |
| peft_integration.md | 23.9 kB | | 6ca1bd1b |
| ppo_trainer.html | 278 kB | | 5560db07 |
| ppo_trainer.md | 41.4 kB | | 2fe6b397 |
| prm_trainer.html | 117 kB | | 9ec48e51 |
| prm_trainer.md | 13.9 kB | | 997f15cb |
| ptt_integration.html | 29.3 kB | | f834e768 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 084950eb |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | 3108a0cc |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | 9fcce65e |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
| reward_trainer.html | 175 kB | | 1642759b |
| reward_trainer.md | 21.5 kB | | 327708f9 |
|