| _app | | | 141 items |
| _toctree.yml | 3.29 kB | | 3ae9d845 |
| async_grpo_trainer.html | 108 kB | | 133b6cef |
| async_grpo_trainer.md | 12.3 kB | | d789ea95 |
| bco_trainer.html | 130 kB | | 5d059771 |
| bco_trainer.md | 14.1 kB | | 84a45cb0 |
| bema_for_reference_model.html | 90 kB | | 6c9184eb |
| bema_for_reference_model.md | 7.18 kB | | 3210d31a |
| callbacks.html | 95.8 kB | | de3d4339 |
| callbacks.md | 7.88 kB | | e6089d85 |
| chat_template_utils.html | 45.5 kB | | 6dee3edc |
| chat_template_utils.md | 5.3 kB | | 00ce91c2 |
| clis.html | 53.4 kB | | 911185ca |
| clis.md | 12.8 kB | | 16f99657 |
| community_tutorials.html | 31 kB | | c8dafc8f |
| community_tutorials.md | 11 kB | | 97fff25c |
| cpo_trainer.html | 144 kB | | 5747d17d |
| cpo_trainer.md | 23 kB | | af7654dc |
| customization.html | 31 kB | | 1f41c314 |
| customization.md | 4.08 kB | | b4d02628 |
| data_utils.html | 62.9 kB | | dd5682f6 |
| data_utils.md | 6.32 kB | | b7b9c858 |
| dataset_formats.html | 223 kB | | c948fd1a |
| dataset_formats.md | 40.2 kB | | 7a1c00fc |
| deepspeed_integration.html | 15.8 kB | | adcb14ac |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | dc109368 |
| distillation_trainer.md | 12.3 kB | | bcb6f02f |
| distributing_training.html | 96.5 kB | | b1ba3b04 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | 4ce56c28 |
| dpo_trainer.md | 30.8 kB | | e11a4e15 |
| example_overview.html | 42.8 kB | | cec1389e |
| example_overview.md | 19.7 kB | | ea1931fb |
| experimental_overview.html | 10.8 kB | | ab74c3b4 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | 5bfe941b |
| gfpo.md | 5.24 kB | | ca1c5d26 |
| gkd_trainer.html | 119 kB | | 0b3485ac |
| gkd_trainer.md | 14.1 kB | | a0e68e6a |
| gold_trainer.html | 166 kB | | 0193edc1 |
| gold_trainer.md | 18.1 kB | | 393a3624 |
| grpo_trainer.html | 560 kB | | b04dd4f0 |
| grpo_trainer.md | 55.4 kB | | 77ef2428 |
| grpo_with_replay_buffer.html | 89.6 kB | | 5b18d4fa |
| grpo_with_replay_buffer.md | 6.16 kB | | 7fc04800 |
| gspo_token.html | 50.2 kB | | e1490bf2 |
| gspo_token.md | 4.27 kB | | 47dd0956 |
| index.html | 29 kB | | 675d71b5 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 9ea5c058 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | b881b7b8 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | 100418dd |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 137 kB | | 5d8f2573 |
| kto_trainer.md | 18.1 kB | | 905cb8e3 |
| liger_kernel_integration.html | 15 kB | | 4e77e18f |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 836 kB | | 83bec8ae |
| llms.txt | 5 kB | | 31e8dd77 |
| lora_without_regret.html | 45 kB | | dbd7c7fd |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 99618acf |
| merge_model_callback.md | 1.19 kB | | f53823a4 |
| minillm_trainer.html | 179 kB | | e2949aef |
| minillm_trainer.md | 16.4 kB | | ce8af0b8 |
| nash_md_trainer.html | 124 kB | | 87b83592 |
| nash_md_trainer.md | 16.3 kB | | 92c6b070 |
| nemo_gym.html | 58.5 kB | | 258a2020 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.41 kB | | 69ac7eab |
| online_dpo_trainer.html | 179 kB | | 8d1a404e |
| online_dpo_trainer.md | 23.1 kB | | 85d225f2 |
| openenv.html | 114 kB | | 085ceedc |
| openenv.md | 27.8 kB | | d269dada |
| orpo_trainer.html | 127 kB | | 22928209 |
| orpo_trainer.md | 17.7 kB | | 65adae16 |
| paper_index.html | 734 kB | | c219c1f0 |
| paper_index.md | 19.1 kB | | 531267a2 |
| papo_trainer.html | 111 kB | | bb211d1a |
| papo_trainer.md | 8.82 kB | | 6ae6ce14 |
| peft_integration.html | 131 kB | | 864f4c1d |
| peft_integration.md | 23.9 kB | | 09c89a81 |
| ppo_trainer.html | 278 kB | | a99b0a79 |
| ppo_trainer.md | 41.4 kB | | 681da20d |
| prm_trainer.html | 117 kB | | 8e267932 |
| prm_trainer.md | 13.9 kB | | 03effd5f |
| ptt_integration.html | 29.3 kB | | 581b3656 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 20d85be7 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | e66c72fb |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | fea67aa6 |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
| reward_trainer.html | 175 kB | | a7f9b349 |
| reward_trainer.md | 21.5 kB | | 7f5d7438 |
|