| _app | | | 221 items |
| _toctree.yml | 3.44 kB | | 84481523 |
| a2po_trainer.html | 102 kB | | 221c81d6 |
| a2po_trainer.md | 14.1 kB | | e5fc6934 |
| async_grpo_trainer.html | 150 kB | | 19b1d75d |
| async_grpo_trainer.md | 29.1 kB | | 233c5796 |
| bco_trainer.html | 133 kB | | 0dadc5d5 |
| bco_trainer.md | 18.2 kB | | 9717f719 |
| bema_for_reference_model.html | 91.5 kB | | 7a9d72c1 |
| bema_for_reference_model.md | 5.71 kB | | 67a5f618 |
| callbacks.html | 97.4 kB | | 549153a0 |
| callbacks.md | 7.37 kB | | 2903ccd7 |
| chat_template_utils.html | 45.9 kB | | 0526a05a |
| chat_template_utils.md | 5.81 kB | | 36bb03b6 |
| chat_templates.html | 62.5 kB | | f492cb0a |
| chat_templates.md | 13.1 kB | | f57b805f |
| clis.html | 53.6 kB | | d90744ee |
| clis.md | 12.8 kB | | e9e2383d |
| community_tutorials.html | 30.8 kB | | 9930de3f |
| community_tutorials.md | 11 kB | | 0141060d |
| cpo_trainer.html | 144 kB | | b51f56d8 |
| cpo_trainer.md | 26.6 kB | | 3ad8ac87 |
| customization.html | 30.6 kB | | fb14fd49 |
| customization.md | 4.08 kB | | 13b13acb |
| data_utils.html | 61.7 kB | | dacbd88a |
| data_utils.md | 6.34 kB | | 6963381f |
| dataset_formats.html | 220 kB | | d38fd259 |
| dataset_formats.md | 43 kB | | 1da22186 |
| deepspeed_integration.html | 15.5 kB | | 5c4bb70d |
| deepspeed_integration.md | 1.52 kB | | e5b0fad5 |
| distillation_trainer.html | 153 kB | | 108dae0b |
| distillation_trainer.md | 20.9 kB | | fdcd67e0 |
| distributing_training.html | 94.8 kB | | 4981a1df |
| distributing_training.md | 21 kB | | 2b14cde4 |
| dpo_trainer.html | 236 kB | | 373a0e88 |
| dpo_trainer.md | 43.4 kB | | c575df05 |
| example_overview.html | 45.6 kB | | 40a9b8c5 |
| example_overview.md | 22.6 kB | | 6feefbc4 |
| experimental_overview.html | 10.4 kB | | 349e730d |
| experimental_overview.md | 1.62 kB | | 45d90cc6 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 86.5 kB | | f52bb50e |
| gfpo.md | 11.2 kB | | 9b5d0477 |
| gkd_trainer.html | 118 kB | | 08025ab5 |
| gkd_trainer.md | 18 kB | | be7eb082 |
| gmpo.html | 89 kB | | eb3679fc |
| gmpo.md | 12.7 kB | | 67f09272 |
| gold_trainer.html | 191 kB | | 330d60a1 |
| gold_trainer.md | 30.6 kB | | 1dd91353 |
| grpo_trainer.html | 627 kB | | 9e501263 |
| grpo_trainer.md | 110 kB | | cb929432 |
| grpo_with_replay_buffer.html | 92 kB | | abac0cea |
| grpo_with_replay_buffer.md | 11.6 kB | | 6ec8b600 |
| gspo_token.html | 49.6 kB | | 116cfa8f |
| gspo_token.md | 2.71 kB | | ed4cf9c1 |
| harbor.html | 76.4 kB | | bfae659c |
| harbor.md | 12.7 kB | | 297bdf0b |
| index.html | 29.1 kB | | 194715e4 |
| index.md | 3.92 kB | | 8c3da09b |
| installation.html | 13.7 kB | | f99b292a |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.7 kB | | cc30d692 |
| jobs_training.md | 6.5 kB | | 1912e3c9 |
| kernels_hub.html | 26.2 kB | | 1f9a3b45 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 219 kB | | 2e2d2e3e |
| kto_trainer.md | 39.4 kB | | a0c487f9 |
| liger_kernel_integration.html | 14.8 kB | | 715d5864 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 1.26 MB | | 9f036582 |
| llms.txt | 5.28 kB | | 8ebbc0b7 |
| lora_without_regret.html | 44.1 kB | | 1d5f3231 |
| lora_without_regret.md | 14.3 kB | | e31f56a0 |
| merge_model_callback.html | 17.6 kB | | eca92be7 |
| merge_model_callback.md | 991 Bytes | | ba2b22af |
| minillm_trainer.html | 181 kB | | 793f107f |
| minillm_trainer.md | 23.7 kB | | 2ad2ae72 |
| nash_md_trainer.html | 124 kB | | d380430d |
| nash_md_trainer.md | 20.4 kB | | 9ed70ed5 |
| objects.inv | 2.6 kB | | f8ffb6a1 |
| online_dpo_trainer.html | 180 kB | | 35a0438c |
| online_dpo_trainer.md | 33.3 kB | | c333c939 |
| openenv.html | 134 kB | | 35aa93e4 |
| openenv.md | 34.9 kB | | 4a6f955d |
| openreward.html | 70.4 kB | | 772f0b39 |
| openreward.md | 11.4 kB | | 0f545ebb |
| orpo_trainer.html | 127 kB | | 26415275 |
| orpo_trainer.md | 21 kB | | d16dbd87 |
| paper_index.html | 823 kB | | d584f03b |
| paper_index.md | 92.7 kB | | debd185f |
| peft_integration.html | 130 kB | | 9b53e248 |
| peft_integration.md | 24.2 kB | | 772495e7 |
| ppo_trainer.html | 275 kB | | 4b80472e |
| ppo_trainer.md | 42.6 kB | | 27e61835 |
| prm_trainer.html | 116 kB | | 05869d23 |
| prm_trainer.md | 16.7 kB | | 43820696 |
| ptt_integration.html | 28.9 kB | | de47e802 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.6 kB | | 2602adab |
| quickstart.md | 3.62 kB | | d6c66824 |
|