| _app | | | 172 items |
| _toctree.yml | 3.57 kB | | 60cb764b |
| a2po_trainer.html | 103 kB | | a12b885c |
| a2po_trainer.md | 8.32 kB | | edee4bf8 |
| async_grpo_trainer.html | 145 kB | | 06992ab4 |
| async_grpo_trainer.md | 17.1 kB | | 1f6beb70 |
| bco_trainer.html | 135 kB | | f2146d32 |
| bco_trainer.md | 15.1 kB | | 840d999c |
| bema_for_reference_model.html | 90.1 kB | | a873061d |
| bema_for_reference_model.md | 7.19 kB | | b2d5fb40 |
| callbacks.html | 96 kB | | e4b275bc |
| callbacks.md | 7.9 kB | | f3ca2227 |
| chat_template_utils.html | 47 kB | | cc419607 |
| chat_template_utils.md | 5.95 kB | | 4c395ca2 |
| chat_templates.html | 61.7 kB | | c767ee38 |
| chat_templates.md | 12.5 kB | | 6c52e7b9 |
| clis.html | 53.6 kB | | 6e2386a5 |
| clis.md | 12.8 kB | | bc028c18 |
| community_tutorials.html | 31 kB | | 27f28da9 |
| community_tutorials.md | 11 kB | | 6f406630 |
| cpo_trainer.html | 146 kB | | 2316a0be |
| cpo_trainer.md | 23.5 kB | | 43cbdc78 |
| customization.html | 31.1 kB | | 7e29545f |
| customization.md | 4.08 kB | | 93d2fb50 |
| data_utils.html | 63 kB | | a51b3e86 |
| data_utils.md | 7.01 kB | | a3ce9bc6 |
| dataset_formats.html | 224 kB | | 9da183ca |
| dataset_formats.md | 43 kB | | 54b6b7c2 |
| deepspeed_integration.html | 15.9 kB | | f7b9f8c3 |
| deepspeed_integration.md | 1.52 kB | | e5b0fad5 |
| distillation_trainer.html | 164 kB | | 0ee83606 |
| distillation_trainer.md | 12.3 kB | | 90085971 |
| distributing_training.html | 96.7 kB | | 4adb14f7 |
| distributing_training.md | 21 kB | | 2b14cde4 |
| dpo_trainer.html | 236 kB | | fe503e8a |
| dpo_trainer.md | 31.4 kB | | 007012d6 |
| example_overview.html | 46.3 kB | | 4f78348a |
| example_overview.md | 22.5 kB | | 51afd9eb |
| experimental_overview.html | 10.8 kB | | b46a3b50 |
| experimental_overview.md | 1.62 kB | | 45d90cc6 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 86.4 kB | | 4f2f305b |
| gfpo.md | 5.24 kB | | de2e1cef |
| gkd_trainer.html | 120 kB | | ac391229 |
| gkd_trainer.md | 14.1 kB | | faf3bd64 |
| gmpo.html | 88.8 kB | | 377816af |
| gmpo.md | 6.75 kB | | 1399d593 |
| gold_trainer.html | 186 kB | | 20c358bd |
| gold_trainer.md | 12.9 kB | | baae533a |
| grpo_trainer.html | 587 kB | | 4aa50700 |
| grpo_trainer.md | 65.4 kB | | 61bbc4e3 |
| grpo_with_replay_buffer.html | 91.6 kB | | 20638497 |
| grpo_with_replay_buffer.md | 6.16 kB | | 1b88741c |
| gspo_token.html | 50.2 kB | | 2880b087 |
| gspo_token.md | 4.27 kB | | dc084bfb |
| harbor.html | 77.6 kB | | 8e4f31ae |
| harbor.md | 13.5 kB | | bbfb820d |
| index.html | 29.3 kB | | 558fc21e |
| index.md | 3.9 kB | | 5958328c |
| installation.html | 13.9 kB | | 37e56983 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 33.1 kB | | 13b1b0d6 |
| jobs_training.md | 6.45 kB | | 38e66142 |
| kernels_hub.html | 26.9 kB | | 5b0948f0 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 151 kB | | de3e64e0 |
| kto_trainer.md | 21 kB | | 67024ed2 |
| liger_kernel_integration.html | 15 kB | | 2edb9d46 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 1.02 MB | | 59292f02 |
| llms.txt | 5.51 kB | | 821a531a |
| lora_without_regret.html | 45.1 kB | | 3b25ca1b |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 18 kB | | 9e092ca4 |
| merge_model_callback.md | 1.21 kB | | 28433c33 |
| minillm_trainer.html | 182 kB | | e517a5e6 |
| minillm_trainer.md | 16.5 kB | | e08eac8f |
| nash_md_trainer.html | 126 kB | | e4122d27 |
| nash_md_trainer.md | 16.6 kB | | 308ad6e4 |
| objects.inv | 2.69 kB | | a2184b62 |
| online_dpo_trainer.html | 183 kB | | 856014e3 |
| online_dpo_trainer.md | 23.3 kB | | ddb6193a |
| openenv.html | 116 kB | | c78eac0c |
| openenv.md | 28.2 kB | | df5eff26 |
| openreward.html | 71.5 kB | | c201c026 |
| openreward.md | 11.5 kB | | 572a4d4d |
| orpo_trainer.html | 129 kB | | 3ce9609c |
| orpo_trainer.md | 18.2 kB | | 6031c099 |
| paper_index.html | 813 kB | | b2762f0c |
| paper_index.md | 90 kB | | 192cef94 |
| papo_trainer.html | 114 kB | | 5545fa9b |
| papo_trainer.md | 8.91 kB | | ae23aaac |
| peft_integration.html | 131 kB | | e3da22a2 |
| peft_integration.md | 23.9 kB | | 7096ebbd |
| ppo_trainer.html | 280 kB | | 336abad8 |
| ppo_trainer.md | 42.3 kB | | 182eee6f |
| prm_trainer.html | 118 kB | | ab6beb0c |
| prm_trainer.md | 14.2 kB | | 15b86b67 |
| ptt_integration.html | 29.3 kB | | 459dd686 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
|