| _app | | | 301 items |
| _toctree.yml | 3.31 kB | | 222c63dd |
| a2po_trainer.html | 102 kB | | 97a0dd29 |
| a2po_trainer.md | 16.7 kB | | 527eba6c |
| async_distillation_trainer.html | 173 kB | | 5ad9af7f |
| async_distillation_trainer.md | 53.2 kB | | f0a9bf25 |
| async_grpo_trainer.html | 215 kB | | 784ed9fd |
| async_grpo_trainer.md | 65 kB | | 254fc445 |
| bco_trainer.html | 134 kB | | b57170e5 |
| bco_trainer.md | 21.6 kB | | fdfcd500 |
| bema_for_reference_model.html | 91.5 kB | | de4e524f |
| bema_for_reference_model.md | 7.12 kB | | 8e2ee079 |
| callbacks.html | 97.5 kB | | 8adfdfee |
| callbacks.md | 8.91 kB | | 43a1d2c0 |
| chat_template_utils.html | 46 kB | | 62f73fa6 |
| chat_template_utils.md | 7.07 kB | | 9b26a507 |
| chat_templates.html | 70.2 kB | | c3de5174 |
| chat_templates.md | 15 kB | | 03a58c98 |
| clis.html | 53.9 kB | | 3f94eaad |
| clis.md | 12.9 kB | | 4e247df5 |
| community_tutorials.html | 30.8 kB | | e8573950 |
| community_tutorials.md | 11 kB | | cbf98d3d |
| cpo_trainer.html | 141 kB | | 9abf1348 |
| cpo_trainer.md | 29.1 kB | | 54147ed6 |
| customization.html | 45.5 kB | | 2ed19734 |
| customization.md | 7.5 kB | | f30e37a1 |
| data_utils.html | 59.8 kB | | b5cad2ab |
| data_utils.md | 7.28 kB | | c13014f8 |
| dataset_formats.html | 190 kB | | 32e8c654 |
| dataset_formats.md | 36.8 kB | | 591c2798 |
| deepspeed_integration.html | 15.4 kB | | b946053b |
| deepspeed_integration.md | 1.46 kB | | 0c0b6c40 |
| distillation_trainer.html | 232 kB | | 368bd834 |
| distillation_trainer.md | 40.3 kB | | 63379869 |
| distributing_training.html | 32.6 kB | | 4692d166 |
| distributing_training.md | 4.93 kB | | 2834266a |
| dpo_trainer.html | 238 kB | | 8936f6f4 |
| dpo_trainer.md | 46.9 kB | | 51f26a01 |
| example_overview.html | 32.4 kB | | 9a85e528 |
| example_overview.md | 15.8 kB | | 5c662160 |
| experimental_overview.html | 13.4 kB | | 9dd8f75f |
| experimental_overview.md | 3.04 kB | | 43e69c0b |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gkd_trainer.html | 118 kB | | 4a15c739 |
| gkd_trainer.md | 20.9 kB | | 792107ff |
| gmpo.html | 89.2 kB | | da3af529 |
| gmpo.md | 13.7 kB | | 8df36f64 |
| gold_trainer.html | 192 kB | | fec8881e |
| gold_trainer.md | 33.3 kB | | 47d1ae24 |
| grpo_trainer.html | 634 kB | | 33cfb2e3 |
| grpo_trainer.md | 114 kB | | cdb2685e |
| grpo_with_replay_buffer.html | 92.1 kB | | 7f5d2dd5 |
| grpo_with_replay_buffer.md | 13.1 kB | | 4156d0fe |
| gspo_token.html | 49.6 kB | | bfa20f6c |
| gspo_token.md | 5.29 kB | | c10ef768 |
| harbor.html | 76.4 kB | | 609584e0 |
| harbor.md | 13.8 kB | | 84c6e003 |
| index.html | 36.6 kB | | 43caeb61 |
| index.md | 4.57 kB | | f45595a7 |
| installation.html | 13.7 kB | | 900db346 |
| installation.md | 721 Bytes | | 93a212e0 |
| iw_opd_trainer.html | 143 kB | | 672964e1 |
| iw_opd_trainer.md | 21.4 kB | | 1f0f40d8 |
| jobs_training.html | 58.7 kB | | d3f014a0 |
| jobs_training.md | 17.4 kB | | 12938320 |
| kernels_hub.html | 30.8 kB | | 845784fd |
| kernels_hub.md | 5.67 kB | | 9dc552d3 |
| kto_trainer.html | 220 kB | | d64761cf |
| kto_trainer.md | 42.5 kB | | 0d4241c8 |
| liger_kernel_integration.html | 15.6 kB | | f6fb1017 |
| liger_kernel_integration.md | 2.82 kB | | 7916b88a |
| llms-full.txt | 1.31 MB | | 20dfe0a6 |
| llms.txt | 5.01 kB | | f01fc123 |
| long_context_training.html | 50.5 kB | | 33c78005 |
| long_context_training.md | 13.2 kB | | 7aed03bb |
| lora_without_regret.html | 44.1 kB | | 8ce886aa |
| lora_without_regret.md | 14.3 kB | | e31f56a0 |
| merge_model_callback.html | 17.6 kB | | 13b7403f |
| merge_model_callback.md | 1.39 kB | | e7f697fd |
| minillm_trainer.html | 181 kB | | bc17bc70 |
| minillm_trainer.md | 25.5 kB | | ac088206 |
| nash_md_trainer.html | 120 kB | | 2804b253 |
| nash_md_trainer.md | 22.6 kB | | 7716ce57 |
| objects.inv | 2.22 kB | | 9d84d437 |
| online_dpo_trainer.html | 177 kB | | ca41f63e |
| online_dpo_trainer.md | 35.9 kB | | c5ebd70f |
| openenv.html | 131 kB | | 36c24f01 |
| openenv.md | 35.1 kB | | 346b927b |
| openreward.html | 70.4 kB | | 164e9a12 |
| openreward.md | 11.9 kB | | 0c1f596e |
| orpo_trainer.html | 124 kB | | 7f61b755 |
| orpo_trainer.md | 23.7 kB | | 1be25fb5 |
| paper_index.html | 822 kB | | d35cc81b |
| paper_index.md | 92.5 kB | | 145046b5 |
| peft_integration.html | 119 kB | | 806de393 |
| peft_integration.md | 21.9 kB | | db50288c |
| ppo_trainer.html | 275 kB | | 121b8f3e |
| ppo_trainer.md | 49.6 kB | | cc5598f3 |
| prm_trainer.html | 113 kB | | 14234842 |
| prm_trainer.md | 19.4 kB | | 559cbaad |
|