| _app | | | 436 items |
| _redirects.yml | 38 Bytes | | 4f139b59 |
| _toctree.yml | 3.2 kB | | 97bbf09f |
| a2po_trainer.html | 102 kB | | 4592ee2f |
| a2po_trainer.md | 16.7 kB | | a0517862 |
| async_distillation_trainer.html | 183 kB | | 4ad9c1bd |
| async_distillation_trainer.md | 56.7 kB | | 8c578440 |
| async_grpo_trainer.html | 215 kB | | 7459dd21 |
| async_grpo_trainer.md | 65 kB | | f1dd6569 |
| bco_trainer.html | 134 kB | | a9dd1222 |
| bco_trainer.md | 21.7 kB | | 1ee768e0 |
| bema_for_reference_model.html | 91.5 kB | | 2c642637 |
| bema_for_reference_model.md | 7.12 kB | | 6caaa66a |
| callbacks.html | 97.5 kB | | 44885c09 |
| callbacks.md | 8.91 kB | | 1afbd29a |
| chat_template_utils.html | 45.8 kB | | 49f896ad |
| chat_template_utils.md | 6.88 kB | | a8b7a0f1 |
| chat_templates.html | 76 kB | | 073609ec |
| chat_templates.md | 16.4 kB | | 55764ffa |
| clis.html | 53.9 kB | | a7500660 |
| clis.md | 12.9 kB | | 2697ae19 |
| community_tutorials.html | 30.8 kB | | 2348ee54 |
| community_tutorials.md | 11 kB | | 7a06ba2b |
| cpo_trainer.html | 141 kB | | db4ff737 |
| cpo_trainer.md | 29.1 kB | | 1f63932f |
| customization.html | 45.5 kB | | 2078eea6 |
| customization.md | 7.5 kB | | 0dab2588 |
| data_utils.html | 59.8 kB | | 3cd7a22a |
| data_utils.md | 7.28 kB | | 18f9f5a8 |
| dataset_formats.html | 190 kB | | 6bbab014 |
| dataset_formats.md | 36.8 kB | | 46eb4d42 |
| deepspeed_integration.html | 15.4 kB | | e4fa88ce |
| deepspeed_integration.md | 1.46 kB | | 0c0b6c40 |
| distillation_trainer.html | 232 kB | | 1d004992 |
| distillation_trainer.md | 40.3 kB | | 5178dec8 |
| distributing_training.html | 32.6 kB | | f3a9e583 |
| distributing_training.md | 4.93 kB | | 2834266a |
| dpo_trainer.html | 235 kB | | 45cee301 |
| dpo_trainer.md | 46.1 kB | | 535dc46a |
| example_overview.html | 32.9 kB | | ea576eed |
| example_overview.md | 16 kB | | 6acea76e |
| experimental_overview.html | 13.4 kB | | 5a6e4fed |
| experimental_overview.md | 3.04 kB | | 43e69c0b |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gkd_trainer.html | 118 kB | | 06a3ae96 |
| gkd_trainer.md | 20.9 kB | | 2a7a3cc6 |
| gmpo.html | 89.2 kB | | 2cacef9a |
| gmpo.md | 13.7 kB | | 220c54d0 |
| gold_trainer.html | 192 kB | | 681842eb |
| gold_trainer.md | 33.3 kB | | b9296ae1 |
| grpo_trainer.html | 634 kB | | 72a62fa6 |
| grpo_trainer.md | 114 kB | | b7cb22e1 |
| grpo_with_replay_buffer.html | 92.1 kB | | f35a1bb8 |
| grpo_with_replay_buffer.md | 13.1 kB | | 673a8990 |
| gspo_token.html | 49.6 kB | | 9ce9e4d3 |
| gspo_token.md | 5.29 kB | | c4ac3c99 |
| harbor.html | 76.4 kB | | 97986b75 |
| harbor.md | 13.8 kB | | f8ef636c |
| index.html | 36.3 kB | | 0449f91a |
| index.md | 4.41 kB | | 9819f61e |
| installation.html | 13.7 kB | | 7fd2b1a4 |
| installation.md | 721 Bytes | | 93a212e0 |
| iw_opd_trainer.html | 143 kB | | 5ecc8e58 |
| iw_opd_trainer.md | 21.4 kB | | fe1d2830 |
| jobs_training.html | 58.7 kB | | a4bcb96d |
| jobs_training.md | 17.4 kB | | 12938320 |
| kernels_hub.html | 25.7 kB | | 6e38df69 |
| kernels_hub.md | 4.96 kB | | aabdccae |
| kto_trainer.html | 218 kB | | ec19efeb |
| kto_trainer.md | 41.9 kB | | a9b1ae3e |
| liger_kernel_integration.html | 15.4 kB | | 1dcf9651 |
| liger_kernel_integration.md | 2.82 kB | | dafc23c6 |
| llms-full.txt | 1.28 MB | | 9e3e1cc7 |
| llms.txt | 4.83 kB | | e6e2dfe5 |
| long_context_training.html | 50.5 kB | | 9c508105 |
| long_context_training.md | 13.2 kB | | 1b3ac069 |
| lora_without_regret.html | 44.1 kB | | da9b7def |
| lora_without_regret.md | 14.3 kB | | e31f56a0 |
| merge_model_callback.html | 17.6 kB | | ceb74e91 |
| merge_model_callback.md | 1.39 kB | | e5972f71 |
| minillm_trainer.html | 181 kB | | 373e8e08 |
| minillm_trainer.md | 25.5 kB | | 919c2b11 |
| nash_md_trainer.html | 120 kB | | 46db979a |
| nash_md_trainer.md | 22.6 kB | | 34367802 |
| objects.inv | 2.16 kB | | d22e5f4d |
| online_dpo_trainer.html | 177 kB | | f53347d2 |
| online_dpo_trainer.md | 35.9 kB | | b888932d |
| openenv.html | 133 kB | | ba0c1778 |
| openenv.md | 35.2 kB | | 2da874f3 |
| openreward.html | 72 kB | | 0c82a5fe |
| openreward.md | 13.1 kB | | 5aabdd53 |
| orpo_trainer.html | 124 kB | | e121c2d7 |
| orpo_trainer.md | 23.7 kB | | 2d6daa46 |
| paper_index.html | 819 kB | | 38c03b13 |
| paper_index.md | 92 kB | | 056b2d0b |
| peft_integration.html | 119 kB | | ea8ab83b |
| peft_integration.md | 21.9 kB | | ed619681 |
| prm_trainer.html | 113 kB | | d6aea960 |
| prm_trainer.md | 19.4 kB | | c1f63d73 |
| quickstart.html | 37.6 kB | | 57cb4108 |
|