| _app | | | 138 items |
| _toctree.yml | 3.15 kB | | 23c10302 |
| bco_trainer.html | 142 kB | | 2411ae07 |
| bco_trainer.md | 14.3 kB | | 16fb0443 |
| bema_for_reference_model.html | 91.3 kB | | 9cb89ca4 |
| bema_for_reference_model.md | 7.7 kB | | 3b66d85c |
| callbacks.html | 101 kB | | bd5a64a3 |
| callbacks.md | 8.14 kB | | 09dbde9e |
| chat_template_utils.html | 69.6 kB | | 3f444a61 |
| chat_template_utils.md | 7.34 kB | | e5330e9d |
| clis.html | 53.4 kB | | fb3dcb35 |
| clis.md | 12.8 kB | | 490ae746 |
| community_tutorials.html | 30.3 kB | | 754aaae9 |
| community_tutorials.md | 10.4 kB | | 1711783a |
| cpo_trainer.html | 154 kB | | 620b9767 |
| cpo_trainer.md | 22.9 kB | | 35c946d1 |
| customization.html | 37.4 kB | | 64f4d90d |
| customization.md | 4.9 kB | | 915a7a8a |
| data_utils.html | 177 kB | | fd7ecc83 |
| data_utils.md | 18.8 kB | | 4f64058b |
| dataset_formats.html | 219 kB | | eacb3fa0 |
| dataset_formats.md | 41.2 kB | | 375f1f22 |
| deepspeed_integration.html | 15.9 kB | | 2244ebde |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distributing_training.html | 80.9 kB | | 5cb1b19c |
| distributing_training.md | 18.8 kB | | 3b39fd9e |
| dpo_trainer.html | 249 kB | | b0b81f00 |
| dpo_trainer.md | 34.9 kB | | 1fa7e480 |
| example_overview.html | 34.3 kB | | 9abb6bd8 |
| example_overview.md | 15.1 kB | | 19e0c85f |
| experimental_overview.html | 10.8 kB | | 57a3da38 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 89 kB | | 88f9b8cf |
| gfpo.md | 5.35 kB | | 992a6e03 |
| gkd_trainer.html | 123 kB | | 3d199598 |
| gkd_trainer.md | 13.9 kB | | 30d00ba4 |
| gold_trainer.html | 144 kB | | caa2d81e |
| gold_trainer.md | 13.8 kB | | dbec876d |
| grpo_trainer.html | 525 kB | | d2e1f867 |
| grpo_trainer.md | 46.7 kB | | b8f63a26 |
| grpo_with_replay_buffer.html | 94.3 kB | | 519d5ff9 |
| grpo_with_replay_buffer.md | 6.27 kB | | 75a55b7e |
| gspo_token.html | 50.6 kB | | c92f54a0 |
| gspo_token.md | 4.38 kB | | e0c54ca8 |
| index.html | 28.6 kB | | b29751d5 |
| index.md | 3.68 kB | | a08ded5f |
| installation.html | 13.9 kB | | 0c3dcecc |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 4f730fe2 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| judges.html | 119 kB | | 06844b9b |
| judges.md | 15 kB | | 8ea96531 |
| kernels_hub.html | 26.8 kB | | 6e3bc392 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 159 kB | | 19af8427 |
| kto_trainer.md | 20.7 kB | | 234d20e3 |
| liger_kernel_integration.html | 15 kB | | a9a91d11 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 809 kB | | c274eb91 |
| llms.txt | 4.76 kB | | 93054b45 |
| lora_without_regret.html | 45.1 kB | | 9120c364 |
| lora_without_regret.md | 14.5 kB | | 38851bd7 |
| merge_model_callback.html | 17.8 kB | | 796934ea |
| merge_model_callback.md | 1.19 kB | | fc80e768 |
| minillm_trainer.html | 184 kB | | 4de6695a |
| minillm_trainer.md | 16.5 kB | | e82ed2c8 |
| model_utils.html | 40.7 kB | | 0e2c980e |
| model_utils.md | 3.42 kB | | 699f71e6 |
| nash_md_trainer.html | 134 kB | | 11d928de |
| nash_md_trainer.md | 16.7 kB | | edb1450d |
| objects.inv | 2.57 kB | | 7104960a |
| online_dpo_trainer.html | 195 kB | | 11ccab23 |
| online_dpo_trainer.md | 25.5 kB | | 04e3bb60 |
| openenv.html | 86.4 kB | | cfbe15c2 |
| openenv.md | 24.9 kB | | 12093e14 |
| orpo_trainer.html | 136 kB | | 9c48ee5b |
| orpo_trainer.md | 17.6 kB | | aaf5d39c |
| others.html | 27.7 kB | | c8d9f5de |
| others.md | 1.83 kB | | bc6d61e9 |
| paper_index.html | 401 kB | | f768e1a5 |
| paper_index.md | 26.2 kB | | 3df890e6 |
| papo_trainer.html | 116 kB | | 37297b31 |
| papo_trainer.md | 8.83 kB | | 47a65a55 |
| peft_integration.html | 131 kB | | 52d8df5f |
| peft_integration.md | 23.8 kB | | 575f6bb6 |
| ppo_trainer.html | 284 kB | | 2d669712 |
| ppo_trainer.md | 41.3 kB | | 99e59533 |
| prm_trainer.html | 123 kB | | 6d9af1a9 |
| prm_trainer.md | 13.7 kB | | e2fdced4 |
| quickstart.html | 37.7 kB | | d50bce81 |
| quickstart.md | 3.36 kB | | 1a8bc789 |
| rapidfire_integration.html | 81.2 kB | | 68779387 |
| rapidfire_integration.md | 12.8 kB | | 33fdfe4a |
| reducing_memory_usage.html | 52.7 kB | | 079330a8 |
| reducing_memory_usage.md | 11.7 kB | | f0145ff0 |
| reward_trainer.html | 198 kB | | 41a66169 |
| reward_trainer.md | 23.4 kB | | e6b2ee4a |
| rewards.html | 75.8 kB | | f7ac0712 |
| rewards.md | 6.31 kB | | 9c0358fa |
|