| _app | | | 276 items |
| _toctree.yml | 3.48 kB | | 41d98fcc |
| a2po_trainer.html | 101 kB | | a8980435 |
| a2po_trainer.md | 8.32 kB | | 8de2a0a9 |
| async_grpo_trainer.html | 134 kB | | af9ee440 |
| async_grpo_trainer.md | 16.5 kB | | d96d7016 |
| bco_trainer.html | 130 kB | | d3b8ad96 |
| bco_trainer.md | 14.2 kB | | b7cebde6 |
| bema_for_reference_model.html | 90 kB | | 4811720c |
| bema_for_reference_model.md | 7.18 kB | | 981ce022 |
| callbacks.html | 95.8 kB | | 490fd3c2 |
| callbacks.md | 7.88 kB | | 09d94714 |
| chat_template_utils.html | 46.8 kB | | 5cc15b1d |
| chat_template_utils.md | 5.92 kB | | 9de5a254 |
| chat_templates.html | 59.9 kB | | 25622ed7 |
| chat_templates.md | 12.1 kB | | 051ae2d2 |
| clis.html | 53.6 kB | | 3c03d518 |
| clis.md | 12.8 kB | | 3014ee52 |
| community_tutorials.html | 31 kB | | d3fed475 |
| community_tutorials.md | 11 kB | | 4ba720e8 |
| cpo_trainer.html | 145 kB | | d375daac |
| cpo_trainer.md | 23.2 kB | | 76c6dd84 |
| customization.html | 31.1 kB | | ba55f6e4 |
| customization.md | 4.08 kB | | 2c1ed2d3 |
| data_utils.html | 62.8 kB | | affec275 |
| data_utils.md | 6.87 kB | | b45b7076 |
| dataset_formats.html | 224 kB | | 6180c32e |
| dataset_formats.md | 43 kB | | 479b72cc |
| deepspeed_integration.html | 15.9 kB | | 50bd0ba7 |
| deepspeed_integration.md | 1.52 kB | | e5b0fad5 |
| distillation_trainer.html | 161 kB | | 141f1ad6 |
| distillation_trainer.md | 12.3 kB | | b8974f62 |
| distributing_training.html | 96.7 kB | | a0f35330 |
| distributing_training.md | 21 kB | | 2b14cde4 |
| dpo_trainer.html | 233 kB | | b48ac107 |
| dpo_trainer.md | 31.1 kB | | 970482fc |
| example_overview.html | 42.7 kB | | 5d5fbd55 |
| example_overview.md | 19.6 kB | | 5dbf6a8f |
| experimental_overview.html | 10.8 kB | | 2a627acd |
| experimental_overview.md | 1.62 kB | | 45d90cc6 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 85.5 kB | | 45e0db96 |
| gfpo.md | 5.24 kB | | 3cae21c0 |
| gkd_trainer.html | 119 kB | | 0b036dc4 |
| gkd_trainer.md | 14.1 kB | | 01c5d558 |
| gold_trainer.html | 167 kB | | 387287d2 |
| gold_trainer.md | 12.9 kB | | 7a41467e |
| grpo_trainer.html | 572 kB | | b9e5c545 |
| grpo_trainer.md | 62.3 kB | | a09079c7 |
| grpo_with_replay_buffer.html | 90.7 kB | | 679bb7e5 |
| grpo_with_replay_buffer.md | 6.16 kB | | 8641205b |
| gspo_token.html | 50.2 kB | | 1756c020 |
| gspo_token.md | 4.27 kB | | e3ef72f4 |
| index.html | 29 kB | | ac9a3b21 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | be18571e |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 33.1 kB | | 98c09efa |
| jobs_training.md | 6.46 kB | | cb814663 |
| kernels_hub.html | 26.9 kB | | fa8e2375 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 136 kB | | 0f8ddd92 |
| kto_trainer.md | 18.5 kB | | 1cc612bf |
| liger_kernel_integration.html | 15 kB | | d7191110 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 974 kB | | 4c29a868 |
| llms.txt | 5.34 kB | | 6aad162d |
| lora_without_regret.html | 45.1 kB | | f14be424 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 2cbbc75e |
| merge_model_callback.md | 1.19 kB | | 04b9d8b0 |
| minillm_trainer.html | 180 kB | | c4aef420 |
| minillm_trainer.md | 16.5 kB | | 4a320378 |
| nash_md_trainer.html | 125 kB | | 290f11c3 |
| nash_md_trainer.md | 16.6 kB | | 3e26e3e0 |
| objects.inv | 2.59 kB | | 5ce8102c |
| online_dpo_trainer.html | 180 kB | | 9969a534 |
| online_dpo_trainer.md | 23.3 kB | | 6ec3de5b |
| openenv.html | 114 kB | | 7092d8eb |
| openenv.md | 27.8 kB | | 03eb6498 |
| openreward.html | 71.5 kB | | fd0a7014 |
| openreward.md | 11.5 kB | | 970197c7 |
| orpo_trainer.html | 128 kB | | b7a14071 |
| orpo_trainer.md | 17.9 kB | | df0cfb20 |
| paper_index.html | 776 kB | | 726aabe7 |
| paper_index.md | 86.8 kB | | 0681ce01 |
| papo_trainer.html | 112 kB | | 45a15683 |
| papo_trainer.md | 8.82 kB | | abcf6168 |
| peft_integration.html | 131 kB | | 075ee49e |
| peft_integration.md | 23.9 kB | | 5c64f8dc |
| ppo_trainer.html | 279 kB | | 9523c050 |
| ppo_trainer.md | 41.5 kB | | 8a8872ac |
| prm_trainer.html | 118 kB | | 8f9ec883 |
| prm_trainer.md | 14.2 kB | | f54f159c |
| ptt_integration.html | 29.3 kB | | cbcc27b1 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.7 kB | | 3db3f0e1 |
| quickstart.md | 3.62 kB | | 5adf1d8b |
| rapidfire_integration.html | 95.6 kB | | f54acb1c |
| rapidfire_integration.md | 17.8 kB | | 4f58dc65 |
|