| _app | | | 138 items |
| _toctree.yml | 3.43 kB | | 4aa162d5 |
| async_grpo_trainer.html | 108 kB | | d465736c |
| async_grpo_trainer.md | 12.3 kB | | 1ef1ad66 |
| bco_trainer.html | 131 kB | | d216f831 |
| bco_trainer.md | 14.2 kB | | 55f3db0a |
| bema_for_reference_model.html | 90 kB | | 1a0c8a23 |
| bema_for_reference_model.md | 7.18 kB | | 10daf295 |
| callbacks.html | 95.8 kB | | cbc6899e |
| callbacks.md | 7.88 kB | | 019d7864 |
| chat_template_utils.html | 46.7 kB | | d3308f68 |
| chat_template_utils.md | 5.87 kB | | 5ab62b8d |
| chat_templates.html | 44.7 kB | | 7ec8b773 |
| chat_templates.md | 8.74 kB | | 1bd72ef5 |
| clis.html | 53.6 kB | | 611ba3a8 |
| clis.md | 12.8 kB | | 4ef429f2 |
| community_tutorials.html | 31 kB | | b6568c12 |
| community_tutorials.md | 11 kB | | d0ef4321 |
| cpo_trainer.html | 145 kB | | 9daeeabe |
| cpo_trainer.md | 23.2 kB | | e7181adf |
| customization.html | 31.1 kB | | 24bb3336 |
| customization.md | 4.08 kB | | 0b1927c3 |
| data_utils.html | 62.8 kB | | 20fbacea |
| data_utils.md | 6.87 kB | | 6dcec2f0 |
| dataset_formats.html | 224 kB | | 19404aa9 |
| dataset_formats.md | 43 kB | | e1e1e1e5 |
| deepspeed_integration.html | 15.9 kB | | b1f820ba |
| deepspeed_integration.md | 1.52 kB | | e5b0fad5 |
| distillation_trainer.html | 161 kB | | 9600609b |
| distillation_trainer.md | 12.3 kB | | 1558f4cd |
| distributing_training.html | 96.7 kB | | f99ac767 |
| distributing_training.md | 21 kB | | 75949925 |
| dpo_trainer.html | 233 kB | | 19e37b04 |
| dpo_trainer.md | 31.1 kB | | b36a01a1 |
| example_overview.html | 42.8 kB | | 811c0c4d |
| example_overview.md | 19.7 kB | | 3c074e34 |
| experimental_overview.html | 10.8 kB | | 9221b25e |
| experimental_overview.md | 1.62 kB | | 45d90cc6 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 85.1 kB | | 3c04b847 |
| gfpo.md | 5.24 kB | | 6bc0d19e |
| gkd_trainer.html | 119 kB | | 249cd9cc |
| gkd_trainer.md | 14.1 kB | | 0c21d278 |
| gold_trainer.html | 166 kB | | d18be7ee |
| gold_trainer.md | 18.1 kB | | a64a74e0 |
| grpo_trainer.html | 562 kB | | 917882e7 |
| grpo_trainer.md | 61.6 kB | | de73b549 |
| grpo_with_replay_buffer.html | 90.3 kB | | cb0e0ff3 |
| grpo_with_replay_buffer.md | 6.16 kB | | 2ffc8196 |
| gspo_token.html | 50.2 kB | | d5699cd9 |
| gspo_token.md | 4.27 kB | | 29c84bbb |
| index.html | 29 kB | | b6406e7f |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | adc390f3 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 33.1 kB | | 0054bf06 |
| jobs_training.md | 6.46 kB | | cb814663 |
| kernels_hub.html | 26.9 kB | | 21bddae5 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 134 kB | | ff4e58ae |
| kto_trainer.md | 18.2 kB | | ebcf9a57 |
| liger_kernel_integration.html | 15 kB | | 6a272f09 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 961 kB | | 3092e244 |
| llms.txt | 5.27 kB | | 200e3ec1 |
| lora_without_regret.html | 45.1 kB | | 2a74858e |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 7c9c8445 |
| merge_model_callback.md | 1.19 kB | | 2dededbe |
| minillm_trainer.html | 180 kB | | 287096e4 |
| minillm_trainer.md | 16.4 kB | | 296b87f6 |
| nash_md_trainer.html | 125 kB | | ed6313c8 |
| nash_md_trainer.md | 16.6 kB | | aa40e1b4 |
| nemo_gym.html | 58.7 kB | | e01b3853 |
| nemo_gym.md | 10.3 kB | | 45caccd9 |
| objects.inv | 2.47 kB | | 4c2ee0e4 |
| online_dpo_trainer.html | 180 kB | | f1fbe42d |
| online_dpo_trainer.md | 23.3 kB | | a2940169 |
| openenv.html | 114 kB | | 80693724 |
| openenv.md | 27.8 kB | | eed86e0a |
| openreward.html | 67.4 kB | | 4268284c |
| openreward.md | 10.6 kB | | 412a398b |
| orpo_trainer.html | 128 kB | | 4b3a1c9f |
| orpo_trainer.md | 17.9 kB | | f35a8b08 |
| paper_index.html | 763 kB | | 4d1b7d94 |
| paper_index.md | 85.1 kB | | 903b7236 |
| papo_trainer.html | 112 kB | | 4655d794 |
| papo_trainer.md | 8.82 kB | | 2883c6e8 |
| peft_integration.html | 131 kB | | 97dcfdf7 |
| peft_integration.md | 23.9 kB | | 7a26154f |
| ppo_trainer.html | 279 kB | | 9d3eb52c |
| ppo_trainer.md | 41.5 kB | | a799aa5b |
| prm_trainer.html | 118 kB | | 5413f3c2 |
| prm_trainer.md | 14.2 kB | | 4bc1ff3a |
| ptt_integration.html | 29.3 kB | | b72bf66a |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.5 kB | | fd6ffbcc |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 95.6 kB | | 33c8b8f6 |
| rapidfire_integration.md | 17.8 kB | | b0dd6d2b |
|