| _app | | | 124 items |
| _toctree.yml | 2.66 kB | | 141860cc |
| bco_trainer.html | 142 kB | | 703da1b6 |
| bco_trainer.md | 27.7 kB | | cbe3b6c1 |
| best_of_n.html | 47.3 kB | | c64cb4ca |
| best_of_n.md | 7.29 kB | | f7775d53 |
| callbacks.html | 131 kB | | 3a6a9ff0 |
| callbacks.md | 15.8 kB | | cf1bb628 |
| clis.html | 45.7 kB | | 85bb06ee |
| clis.md | 9.37 kB | | d13f8859 |
| community_tutorials.html | 27.1 kB | | 39103322 |
| community_tutorials.md | 10.3 kB | | d6b2f859 |
| cpo_trainer.html | 154 kB | | ac58b001 |
| cpo_trainer.md | 35.9 kB | | b3a2869f |
| customization.html | 26.4 kB | | dd401689 |
| customization.md | 4.6 kB | | f4b3632e |
| data_utils.html | 164 kB | | 8dd54fda |
| data_utils.md | 22.6 kB | | 3b129d2f |
| dataset_formats.html | 233 kB | | 37038071 |
| dataset_formats.md | 47.3 kB | | c49ce9ec |
| deepspeed_integration.html | 15.9 kB | | f8599578 |
| deepspeed_integration.md | 1.63 kB | | 29c8b2bd |
| distributing_training.html | 43.2 kB | | 7c0ddd87 |
| distributing_training.md | 9.82 kB | | 09ac1cc8 |
| dpo_trainer.html | 251 kB | | 6c116fe5 |
| dpo_trainer.md | 61.4 kB | | 5b03fac2 |
| example_overview.html | 32.7 kB | | a9ddd369 |
| example_overview.md | 12 kB | | 51a1d5de |
| experimental.html | 40.6 kB | | 8e0819fe |
| experimental.md | 6.53 kB | | 7e69ae86 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gkd_trainer.html | 123 kB | | e40fadca |
| gkd_trainer.md | 27.4 kB | | 9b42bfbc |
| grpo_trainer.html | 420 kB | | 84abf4fe |
| grpo_trainer.md | 75.1 kB | | d2280370 |
| index.html | 26.7 kB | | bbffd419 |
| index.md | 8.13 kB | | e38d7b0e |
| installation.html | 13.9 kB | | 2418cef4 |
| installation.md | 924 Bytes | | a54d5614 |
| jobs_training.html | 32.9 kB | | b5174c2e |
| jobs_training.md | 7.24 kB | | 5e32c47d |
| judges.html | 119 kB | | 13c5fc0a |
| judges.md | 15.8 kB | | 45d695ea |
| kernels_hub.html | 26.8 kB | | d52f99e1 |
| kernels_hub.md | 4.79 kB | | aa7afb04 |
| kto_trainer.html | 158 kB | | 88b8d2d5 |
| kto_trainer.md | 34.2 kB | | b95a327a |
| liger_kernel_integration.html | 10.9 kB | | 7634c9e3 |
| liger_kernel_integration.md | 1.77 kB | | 3077046c |
| llms-full.txt | 982 kB | | a448630d |
| llms.txt | 4.12 kB | | 42c7eddf |
| lora_without_regret.html | 52.3 kB | | a7f0b365 |
| lora_without_regret.md | 18.2 kB | | db874715 |
| model_utils.html | 39.4 kB | | 15504ba6 |
| model_utils.md | 5.76 kB | | 42f40816 |
| models.html | 128 kB | | a5af27a5 |
| models.md | 20.2 kB | | a9cd228f |
| multi_adapter_rl.html | 24.3 kB | | d4774257 |
| multi_adapter_rl.md | 3.91 kB | | 4345e603 |
| nash_md_trainer.html | 136 kB | | 23eaec78 |
| nash_md_trainer.md | 31.1 kB | | 9ba6f974 |
| objects.inv | 2.15 kB | | a7fe59ee |
| online_dpo_trainer.html | 198 kB | | c372bb62 |
| online_dpo_trainer.md | 46.6 kB | | b2b51db4 |
| orpo_trainer.html | 136 kB | | fa0f2e2e |
| orpo_trainer.md | 30.9 kB | | a079757c |
| others.html | 27.7 kB | | c2f3bdd7 |
| others.md | 2.7 kB | | 5e2080c6 |
| paper_index.html | 232 kB | | 5df1e4f5 |
| paper_index.md | 24.7 kB | | 3dd6c56b |
| peft_integration.html | 36.8 kB | | 886c944f |
| peft_integration.md | 5.45 kB | | 15c30f91 |
| ppo_trainer.html | 144 kB | | c3d67859 |
| ppo_trainer.md | 38.2 kB | | 2f563f32 |
| prm_trainer.html | 123 kB | | 5475cb82 |
| prm_trainer.md | 25.9 kB | | a4ea244a |
| quickstart.html | 38.1 kB | | 9a5280b0 |
| quickstart.md | 3.7 kB | | 8bee82e9 |
| reducing_memory_usage.html | 42 kB | | fd027e46 |
| reducing_memory_usage.md | 9.98 kB | | 7d4f9206 |
| reward_trainer.html | 198 kB | | 44f00793 |
| reward_trainer.md | 39.2 kB | | 9b8de98e |
| rewards.html | 58.9 kB | | a5fc97b0 |
| rewards.md | 5.62 kB | | 9bff5b1b |
| rloo_trainer.html | 397 kB | | 1ca8ac81 |
| rloo_trainer.md | 75.2 kB | | 41a0ee3a |
| script_utils.html | 102 kB | | 17037c83 |
| script_utils.md | 13.7 kB | | 4a3c212d |
| sentiment_tuning.html | 13.5 kB | | 1fd21ecc |
| sentiment_tuning.md | 2.68 kB | | d415e4f6 |
| sft_trainer.html | 269 kB | | cf14cc27 |
| sft_trainer.md | 56.8 kB | | c66b4254 |
| speeding_up_training.html | 12 kB | | 1c178f4a |
| speeding_up_training.md | 2.93 kB | | b985e674 |
| trackio_integration.html | 18.8 kB | | af72644a |
| trackio_integration.md | 2.23 kB | | ec250be7 |
| unsloth_integration.html | 31.7 kB | | ccd40944 |
| unsloth_integration.md | 5.34 kB | | 318e047d |
| use_model.html | 17.5 kB | | c56e292f |
| use_model.md | 2.66 kB | | 4bb0671e |
|