| _app | | | 137 items |
| _toctree.yml | 3.38 kB | | 9da8f3eb |
| async_grpo_trainer.html | 108 kB | | ea8948a8 |
| async_grpo_trainer.md | 12.3 kB | | 09889169 |
| bco_trainer.html | 130 kB | | b5b236cd |
| bco_trainer.md | 14.2 kB | | 26b9f69d |
| bema_for_reference_model.html | 90 kB | | 1b21c2a5 |
| bema_for_reference_model.md | 7.18 kB | | e4f792e9 |
| callbacks.html | 95.8 kB | | c22e4ae5 |
| callbacks.md | 7.88 kB | | d5626d2f |
| chat_template_utils.html | 46.2 kB | | cae11b38 |
| chat_template_utils.md | 5.8 kB | | 83be3473 |
| chat_templates.html | 42.6 kB | | 7bb36320 |
| chat_templates.md | 8.22 kB | | 0b6c5d88 |
| clis.html | 53.4 kB | | 9cde4f3f |
| clis.md | 12.8 kB | | e4f2a748 |
| community_tutorials.html | 31 kB | | 7cba2a43 |
| community_tutorials.md | 11 kB | | 33e61af9 |
| cpo_trainer.html | 145 kB | | 59b622ca |
| cpo_trainer.md | 23.2 kB | | 4f52867e |
| customization.html | 31 kB | | 8fad3a19 |
| customization.md | 4.08 kB | | cef09dc1 |
| data_utils.html | 62.7 kB | | b6de68b6 |
| data_utils.md | 6.87 kB | | ea4f6c33 |
| dataset_formats.html | 223 kB | | 30b38792 |
| dataset_formats.md | 43 kB | | 2814c5c0 |
| deepspeed_integration.html | 15.8 kB | | fdbe0c86 |
| deepspeed_integration.md | 1.52 kB | | e5b0fad5 |
| distillation_trainer.html | 161 kB | | f0e22e33 |
| distillation_trainer.md | 12.3 kB | | 7eaaf67f |
| distributing_training.html | 96.5 kB | | a3ab15cb |
| distributing_training.md | 21 kB | | 75949925 |
| dpo_trainer.html | 233 kB | | 46064577 |
| dpo_trainer.md | 31.1 kB | | 50026b9d |
| example_overview.html | 42.7 kB | | 242a836d |
| example_overview.md | 19.7 kB | | f0c23a95 |
| experimental_overview.html | 10.8 kB | | 93dcf985 |
| experimental_overview.md | 1.62 kB | | 45d90cc6 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 85 kB | | 77b6117c |
| gfpo.md | 5.24 kB | | e6d36ee7 |
| gkd_trainer.html | 119 kB | | de945d74 |
| gkd_trainer.md | 14.1 kB | | 6abebff1 |
| gold_trainer.html | 166 kB | | aae20b88 |
| gold_trainer.md | 18.1 kB | | df488337 |
| grpo_trainer.html | 561 kB | | 0595575d |
| grpo_trainer.md | 61.5 kB | | 998f6ea7 |
| grpo_with_replay_buffer.html | 90.3 kB | | 4c028ba4 |
| grpo_with_replay_buffer.md | 6.16 kB | | 6bddecf1 |
| gspo_token.html | 50.2 kB | | 5695d27c |
| gspo_token.md | 4.27 kB | | 4f32e13a |
| index.html | 29 kB | | a2ad5b80 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 0d3bb287 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | ea50bc1e |
| jobs_training.md | 6.46 kB | | cb814663 |
| kernels_hub.html | 26.8 kB | | 74fb375c |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 134 kB | | 8d32648a |
| kto_trainer.md | 18.2 kB | | f4fa7a99 |
| liger_kernel_integration.html | 15 kB | | c286b158 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 950 kB | | 50d0e1b3 |
| llms.txt | 5.15 kB | | 76615447 |
| lora_without_regret.html | 45 kB | | 9a1a9171 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 123433e3 |
| merge_model_callback.md | 1.19 kB | | f7b56014 |
| minillm_trainer.html | 180 kB | | 1d86d8c2 |
| minillm_trainer.md | 16.4 kB | | 723cc8d9 |
| nash_md_trainer.html | 125 kB | | edee4574 |
| nash_md_trainer.md | 16.6 kB | | baff062a |
| nemo_gym.html | 58.5 kB | | fbf31bdd |
| nemo_gym.md | 10.3 kB | | 45caccd9 |
| objects.inv | 2.45 kB | | 2a855f19 |
| online_dpo_trainer.html | 180 kB | | c6670b21 |
| online_dpo_trainer.md | 23.3 kB | | bf1c3de5 |
| openenv.html | 114 kB | | 16a62937 |
| openenv.md | 27.8 kB | | 633b2650 |
| orpo_trainer.html | 128 kB | | dcc2d062 |
| orpo_trainer.md | 17.9 kB | | 6952229a |
| paper_index.html | 761 kB | | 94b64d49 |
| paper_index.md | 85.1 kB | | fe17b5c4 |
| papo_trainer.html | 112 kB | | 24d79c9d |
| papo_trainer.md | 8.82 kB | | 3b3b99e2 |
| peft_integration.html | 131 kB | | a90637c4 |
| peft_integration.md | 23.9 kB | | 37c09ce5 |
| ppo_trainer.html | 279 kB | | ec87ed8a |
| ppo_trainer.md | 41.5 kB | | c16abdab |
| prm_trainer.html | 118 kB | | 7460f0ad |
| prm_trainer.md | 14.2 kB | | 44dbe6db |
| ptt_integration.html | 29.3 kB | | 7d4c40b2 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 18cb5dba |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 95.4 kB | | de33a3d9 |
| rapidfire_integration.md | 17.8 kB | | b0dd6d2b |
| reducing_memory_usage.html | 57.1 kB | | f94af0cc |
| reducing_memory_usage.md | 13.7 kB | | 88a18742 |
|