| _app | | | 147 items |
| _toctree.yml | 3.15 kB | | 23c10302 |
| bco_trainer.html | 142 kB | | b7b1759d |
| bco_trainer.md | 14.3 kB | | f8a25a5b |
| bema_for_reference_model.html | 91.3 kB | | dd14c1bd |
| bema_for_reference_model.md | 7.7 kB | | e1a4f723 |
| callbacks.html | 101 kB | | f9e5ac35 |
| callbacks.md | 8.14 kB | | 6f805695 |
| chat_template_utils.html | 69.1 kB | | 06e5cf4d |
| chat_template_utils.md | 7.22 kB | | 6f9b321e |
| clis.html | 53.4 kB | | 30308727 |
| clis.md | 12.8 kB | | e9ae5dab |
| community_tutorials.html | 31 kB | | 0c3431ff |
| community_tutorials.md | 10.9 kB | | 8f6f87ed |
| cpo_trainer.html | 154 kB | | 8e7f8b7c |
| cpo_trainer.md | 22.9 kB | | f878adfb |
| customization.html | 37.4 kB | | cd467ed1 |
| customization.md | 4.9 kB | | 0c9d8f3c |
| data_utils.html | 177 kB | | 28a5eabd |
| data_utils.md | 18.9 kB | | fec0fbfe |
| dataset_formats.html | 219 kB | | 6706a61c |
| dataset_formats.md | 41.2 kB | | 23b504b6 |
| deepspeed_integration.html | 15.9 kB | | 4c98cb6d |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distributing_training.html | 80.9 kB | | 3e666c11 |
| distributing_training.md | 18.8 kB | | 3b39fd9e |
| dpo_trainer.html | 251 kB | | 489395db |
| dpo_trainer.md | 35.4 kB | | 1ae5fdaf |
| example_overview.html | 35.6 kB | | 82bf6fe9 |
| example_overview.md | 16.2 kB | | f5779dfc |
| experimental_overview.html | 10.8 kB | | 392dc383 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 89.4 kB | | 6f74fc42 |
| gfpo.md | 5.35 kB | | 11815a6b |
| gkd_trainer.html | 123 kB | | f5b342de |
| gkd_trainer.md | 13.9 kB | | 9e9cb4a1 |
| gold_trainer.html | 144 kB | | 80aed160 |
| gold_trainer.md | 13.8 kB | | bb76984e |
| grpo_trainer.html | 536 kB | | 4c943a34 |
| grpo_trainer.md | 48.7 kB | | cd2fb9ce |
| grpo_with_replay_buffer.html | 94.7 kB | | 450661fd |
| grpo_with_replay_buffer.md | 6.27 kB | | b0722eec |
| gspo_token.html | 50.6 kB | | 1f8747ca |
| gspo_token.md | 4.38 kB | | d8655ea7 |
| index.html | 28.6 kB | | 69437d72 |
| index.md | 3.68 kB | | a08ded5f |
| installation.html | 13.9 kB | | 2dca1282 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 8e806b16 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| judges.html | 119 kB | | 0c7f55a1 |
| judges.md | 15 kB | | b761c310 |
| kernels_hub.html | 26.8 kB | | c582cbc2 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 159 kB | | af0169b1 |
| kto_trainer.md | 20.7 kB | | b2b5ed15 |
| liger_kernel_integration.html | 15 kB | | 75d86729 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 818 kB | | 341eff62 |
| llms.txt | 4.76 kB | | 4a019eb9 |
| lora_without_regret.html | 45.1 kB | | 0c2aa638 |
| lora_without_regret.md | 14.5 kB | | 38851bd7 |
| merge_model_callback.html | 17.8 kB | | f0aba91d |
| merge_model_callback.md | 1.19 kB | | f223c2e6 |
| minillm_trainer.html | 184 kB | | 73458e90 |
| minillm_trainer.md | 16.5 kB | | f3218a4a |
| model_utils.html | 40.7 kB | | 5f63c8fa |
| model_utils.md | 3.42 kB | | 4d0b2e71 |
| nash_md_trainer.html | 134 kB | | f04d6ef5 |
| nash_md_trainer.md | 16.7 kB | | 6e1b9cbe |
| objects.inv | 2.57 kB | | de3a168a |
| online_dpo_trainer.html | 195 kB | | eb22808a |
| online_dpo_trainer.md | 25.5 kB | | 41949728 |
| openenv.html | 86.6 kB | | d5cc2b16 |
| openenv.md | 25.1 kB | | 4baa8b1b |
| orpo_trainer.html | 136 kB | | ff703c7d |
| orpo_trainer.md | 17.6 kB | | 00d50de4 |
| others.html | 29.7 kB | | eb9ed487 |
| others.md | 2.18 kB | | 2d73b8ef |
| paper_index.html | 455 kB | | ce5e375f |
| paper_index.md | 28.1 kB | | ec4f51b6 |
| papo_trainer.html | 116 kB | | 5578135f |
| papo_trainer.md | 8.83 kB | | d7716921 |
| peft_integration.html | 131 kB | | 24ffc427 |
| peft_integration.md | 23.8 kB | | 575f6bb6 |
| ppo_trainer.html | 284 kB | | 83cd46af |
| ppo_trainer.md | 41.3 kB | | c5bfc7df |
| prm_trainer.html | 123 kB | | a0859254 |
| prm_trainer.md | 13.7 kB | | d066e6be |
| quickstart.html | 37.7 kB | | b61b1ea2 |
| quickstart.md | 3.36 kB | | 1a8bc789 |
| rapidfire_integration.html | 81.2 kB | | 19f9c9db |
| rapidfire_integration.md | 12.8 kB | | 33fdfe4a |
| reducing_memory_usage.html | 52.7 kB | | e71d5243 |
| reducing_memory_usage.md | 11.7 kB | | 56a7efa7 |
| reward_trainer.html | 199 kB | | ecb5e974 |
| reward_trainer.md | 23.7 kB | | 47001a54 |
| rewards.html | 75.8 kB | | 8fd68343 |
| rewards.md | 6.31 kB | | c94f214c |
|