| _app | | | 464 items |
| _toctree.yml | 3.2 kB | | 97bbf09f |
| a2po_trainer.html | 102 kB | | afabedcf |
| a2po_trainer.md | 16.7 kB | | 88160489 |
| async_distillation_trainer.html | 183 kB | | 39ba56c0 |
| async_distillation_trainer.md | 56.7 kB | | 6e4b8e4f |
| async_grpo_trainer.html | 215 kB | | ad4cc299 |
| async_grpo_trainer.md | 65 kB | | cf7e0fed |
| bema_for_reference_model.html | 91.5 kB | | fb879dd2 |
| bema_for_reference_model.md | 7.12 kB | | 8ca9a0cc |
| callbacks.html | 97.5 kB | | f68dd83d |
| callbacks.md | 8.91 kB | | 0775c8bb |
| chat_template_utils.html | 45.8 kB | | 6dca8e1b |
| chat_template_utils.md | 6.88 kB | | ef1f6816 |
| chat_templates.html | 76 kB | | 08e1d577 |
| chat_templates.md | 16.4 kB | | 8c33e8fc |
| clis.html | 53.9 kB | | b93bd0b9 |
| clis.md | 12.9 kB | | c7568682 |
| community_tutorials.html | 30.8 kB | | 8aff1f63 |
| community_tutorials.md | 11 kB | | d4db73ab |
| cpo_trainer.html | 141 kB | | 5dfc34c8 |
| cpo_trainer.md | 29.1 kB | | 6729e633 |
| customization.html | 45.5 kB | | cc6ea3aa |
| customization.md | 7.5 kB | | 66c2b3a1 |
| data_utils.html | 59.8 kB | | 65287eea |
| data_utils.md | 7.28 kB | | ae791f33 |
| dataset_formats.html | 190 kB | | c9f59536 |
| dataset_formats.md | 36.8 kB | | 2f61642f |
| deepspeed_integration.html | 15.4 kB | | e4fa88ce |
| deepspeed_integration.md | 1.46 kB | | 0c0b6c40 |
| distillation_trainer.html | 232 kB | | 949fa406 |
| distillation_trainer.md | 40.3 kB | | 0115234b |
| distributing_training.html | 32.6 kB | | f3a9e583 |
| distributing_training.md | 4.93 kB | | 2834266a |
| dpo_trainer.html | 236 kB | | f6ea67fc |
| dpo_trainer.md | 46.4 kB | | 4bcfd7dd |
| example_overview.html | 32 kB | | 32cc928d |
| example_overview.md | 15.4 kB | | 135d61da |
| 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 | | bc3a2e4c |
| gkd_trainer.md | 20.9 kB | | aa270048 |
| gmpo.html | 89.2 kB | | 9d3f51f8 |
| gmpo.md | 13.7 kB | | 7cf9ee21 |
| gold_trainer.html | 192 kB | | 9f2ec6f6 |
| gold_trainer.md | 33.3 kB | | a68d2dc2 |
| grpo_trainer.html | 634 kB | | 8460f48f |
| grpo_trainer.md | 114 kB | | a6a01a60 |
| harbor.html | 76.4 kB | | 1f289e49 |
| harbor.md | 13.8 kB | | 9ee27fb7 |
| index.html | 36.5 kB | | c93b1b8b |
| index.md | 4.53 kB | | 01d0f60e |
| installation.html | 13.7 kB | | 7fd2b1a4 |
| installation.md | 721 Bytes | | 93a212e0 |
| iw_opd_trainer.html | 143 kB | | 05635b66 |
| iw_opd_trainer.md | 21.4 kB | | 7a72ce83 |
| jobs_training.html | 58.7 kB | | a4bcb96d |
| jobs_training.md | 17.4 kB | | 12938320 |
| kernels_hub.html | 25.8 kB | | 90b8833a |
| kernels_hub.md | 4.96 kB | | aabdccae |
| kto_trainer.html | 218 kB | | 7bdc70eb |
| kto_trainer.md | 42.2 kB | | 2d145f30 |
| liger_kernel_integration.html | 15.4 kB | | 3fa205d1 |
| liger_kernel_integration.md | 2.66 kB | | 7dbb3d71 |
| llms-full.txt | 1.28 MB | | 7a34656d |
| llms.txt | 4.83 kB | | bfa1d81f |
| long_context_training.html | 50.5 kB | | ff6e70ff |
| long_context_training.md | 13.2 kB | | 5d9bd29e |
| lora_without_regret.html | 44.1 kB | | da9b7def |
| lora_without_regret.md | 14.3 kB | | e31f56a0 |
| merge_model_callback.html | 17.6 kB | | 1c798e0f |
| merge_model_callback.md | 1.39 kB | | e3118068 |
| minillm_trainer.html | 181 kB | | 3a12ba7c |
| minillm_trainer.md | 25.5 kB | | c5caaa67 |
| objects.inv | 2.16 kB | | 7548de04 |
| online_dpo_trainer.html | 177 kB | | a6915468 |
| online_dpo_trainer.md | 35.9 kB | | c7c102bc |
| openenv.html | 133 kB | | ec1444f9 |
| openenv.md | 35.2 kB | | 39afb1bf |
| openreward.html | 72 kB | | a14bb335 |
| openreward.md | 13.1 kB | | f946b83d |
| orpo_trainer.html | 124 kB | | a08e0d30 |
| orpo_trainer.md | 23.7 kB | | d3bc935d |
| paper_index.html | 819 kB | | dbae34ce |
| paper_index.md | 92 kB | | 03533a00 |
| peft_integration.html | 119 kB | | 77f1703d |
| peft_integration.md | 21.9 kB | | 2130d2fc |
| quickstart.html | 37.6 kB | | 57cb4108 |
| quickstart.md | 3.62 kB | | d6c66824 |
| rapidfire_integration.html | 94.2 kB | | 3968f563 |
| rapidfire_integration.md | 17.8 kB | | 337b5dbc |
| reducing_memory_usage.html | 54.1 kB | | 501da0a2 |
| reducing_memory_usage.md | 12.7 kB | | 1b219987 |
| reward_trainer.html | 179 kB | | 344ad3b9 |
| reward_trainer.md | 31.6 kB | | 763b43c3 |
| rewards.html | 123 kB | | ec3d79d4 |
| rewards.md | 12.4 kB | | 7cde3ef4 |
| rloo_trainer.html | 412 kB | | 84b2c3e0 |
| rloo_trainer.md | 68.8 kB | | 82ad3ef8 |
|