| _app | | | 391 items |
| _toctree.yml | 2.66 kB | | 141860cc |
| bco_trainer.html | 142 kB | | 92ad74b3 |
| bco_trainer.md | 27.7 kB | | d6aa3873 |
| best_of_n.html | 47.3 kB | | a3770550 |
| best_of_n.md | 7.29 kB | | 2ada55ba |
| callbacks.html | 131 kB | | f14a80f1 |
| callbacks.md | 15.8 kB | | c8e07728 |
| clis.html | 45.6 kB | | 52f35740 |
| clis.md | 9.32 kB | | fb77c88b |
| community_tutorials.html | 27.1 kB | | 050243f8 |
| community_tutorials.md | 10.3 kB | | 03eb4016 |
| cpo_trainer.html | 154 kB | | 1cb4694b |
| cpo_trainer.md | 35.9 kB | | 313a648f |
| customization.html | 26.4 kB | | c4e4d784 |
| customization.md | 4.6 kB | | 5c252aa4 |
| data_utils.html | 164 kB | | 36028f05 |
| data_utils.md | 22.6 kB | | 0086278f |
| dataset_formats.html | 233 kB | | d4e3d697 |
| dataset_formats.md | 47.3 kB | | ab9173f6 |
| deepspeed_integration.html | 15.9 kB | | 6fe21fcf |
| deepspeed_integration.md | 1.63 kB | | 29c8b2bd |
| distributing_training.html | 43.2 kB | | fb6a2cc5 |
| distributing_training.md | 9.82 kB | | 09ac1cc8 |
| dpo_trainer.html | 251 kB | | a9d3efea |
| dpo_trainer.md | 61.4 kB | | 0bd4c7bc |
| example_overview.html | 32.7 kB | | 59c0cef0 |
| example_overview.md | 12 kB | | 8c76205c |
| experimental.html | 40.6 kB | | a6491e6a |
| experimental.md | 6.53 kB | | 7e69ae86 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gkd_trainer.html | 123 kB | | 1002c900 |
| gkd_trainer.md | 27.4 kB | | ab2564f5 |
| grpo_trainer.html | 420 kB | | 2148c251 |
| grpo_trainer.md | 75.1 kB | | 0604add2 |
| how_to_train.html | 23.1 kB | | 6d681bf9 |
| how_to_train.md | 7.01 kB | | cdf1227f |
| index.html | 26.7 kB | | 9279beef |
| index.md | 8.13 kB | | c2d2825d |
| installation.html | 13.9 kB | | 8f9f0473 |
| installation.md | 924 Bytes | | a54d5614 |
| jobs_training.html | 32.9 kB | | b471aa6b |
| jobs_training.md | 7.24 kB | | 5e32c47d |
| judges.html | 119 kB | | 9376abe8 |
| judges.md | 15.8 kB | | 4c427c2d |
| kernels_hub.html | 26.8 kB | | 5d076aa0 |
| kernels_hub.md | 4.79 kB | | aa7afb04 |
| kto_trainer.html | 158 kB | | 2bfed1ec |
| kto_trainer.md | 34.2 kB | | ad93672b |
| liger_kernel_integration.html | 10.9 kB | | d7c1af5b |
| liger_kernel_integration.md | 1.77 kB | | 0b16a3fe |
| llms-full.txt | 982 kB | | a10c3da8 |
| llms.txt | 4.12 kB | | 74c609fe |
| logging.html | 28.2 kB | | 2a4c6337 |
| logging.md | 9.58 kB | | 926c4680 |
| lora_without_regret.html | 52.3 kB | | e8336ec0 |
| lora_without_regret.md | 18.2 kB | | db874715 |
| model_utils.html | 39.4 kB | | 70cfb428 |
| model_utils.md | 5.76 kB | | c5a8b4ea |
| models.html | 128 kB | | 78834af9 |
| models.md | 20.2 kB | | 3f6e4d16 |
| multi_adapter_rl.html | 24.3 kB | | 4de7b079 |
| multi_adapter_rl.md | 3.91 kB | | 4345e603 |
| nash_md_trainer.html | 136 kB | | bab71112 |
| nash_md_trainer.md | 31.1 kB | | 445931d4 |
| objects.inv | 2.15 kB | | 448dae4c |
| online_dpo_trainer.html | 198 kB | | c3ed85ff |
| online_dpo_trainer.md | 46.6 kB | | 13daede2 |
| orpo_trainer.html | 136 kB | | 2bb078ce |
| orpo_trainer.md | 30.9 kB | | 3124c9e9 |
| others.html | 27.7 kB | | 128e5b3f |
| others.md | 2.7 kB | | 676a2f08 |
| paper_index.html | 232 kB | | c32660ea |
| paper_index.md | 24.7 kB | | 12e02cc2 |
| peft_integration.html | 36.8 kB | | 5d6754a1 |
| peft_integration.md | 5.45 kB | | 15c30f91 |
| ppo_trainer.html | 144 kB | | a9e8c424 |
| ppo_trainer.md | 38.2 kB | | 0fe08289 |
| prm_trainer.html | 123 kB | | 33ae96fd |
| prm_trainer.md | 25.9 kB | | c5f7e16f |
| quickstart.html | 38.1 kB | | 7e49476f |
| quickstart.md | 3.7 kB | | 8bee82e9 |
| reducing_memory_usage.html | 42 kB | | cfdeacc8 |
| reducing_memory_usage.md | 9.98 kB | | 97042ae2 |
| reward_trainer.html | 198 kB | | f25a13c7 |
| reward_trainer.md | 39.2 kB | | a4a9d91d |
| rewards.html | 58.9 kB | | 9e7d9663 |
| rewards.md | 5.62 kB | | 43624844 |
| rloo_trainer.html | 397 kB | | 907323ca |
| rloo_trainer.md | 75.2 kB | | 0edec7fb |
| script_utils.html | 102 kB | | 1c0b0017 |
| script_utils.md | 13.7 kB | | a0cc610e |
| sentiment_tuning.html | 13.5 kB | | 322a9de3 |
| sentiment_tuning.md | 2.68 kB | | d415e4f6 |
| sft_trainer.html | 269 kB | | b62bff38 |
| sft_trainer.md | 56.8 kB | | 428436d9 |
| speeding_up_training.html | 12 kB | | 9be64d43 |
| speeding_up_training.md | 2.93 kB | | b985e674 |
| trackio_integration.html | 18.8 kB | | 2681714a |
| trackio_integration.md | 2.23 kB | | ec250be7 |
|