| _app | | | 68 items |
| _toctree.yml | 2.76 kB | | f088ccd3 |
| alignprop_trainer.html | 25 kB | | d86bfee1 |
| bco_trainer.html | 177 kB | | 1f0b35bb |
| best_of_n.html | 15.7 kB | | 2a78f856 |
| callbacks.html | 57.1 kB | | 39b76269 |
| clis.html | 68.9 kB | | 885b0619 |
| community_tutorials.html | 15.7 kB | | edbb2a1f |
| cpo_trainer.html | 185 kB | | cd043a20 |
| customization.html | 23.9 kB | | eb038264 |
| data_utils.html | 145 kB | | f57d7173 |
| dataset_formats.html | 208 kB | | 45589910 |
| ddpo_trainer.html | 144 kB | | 307cb70a |
| deepspeed_integration.html | 13.8 kB | | e706c74b |
| detoxifying_a_lm.html | 46.3 kB | | 1de3fdb1 |
| distributing_training.html | 15.8 kB | | fdb1da1d |
| dpo_trainer.html | 279 kB | | d2f8b08e |
| example_overview.html | 27.1 kB | | 40f11ffa |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gkd_trainer.html | 91.5 kB | | e5bcd376 |
| grpo_trainer.html | 355 kB | | d0414818 |
| how_to_train.html | 20.7 kB | | 2f8d41da |
| index.html | 12.7 kB | | 2afd25de |
| installation.html | 11.5 kB | | 7d7d8317 |
| iterative_sft_trainer.html | 57.2 kB | | 85dda661 |
| judges.html | 117 kB | | 17d179c7 |
| kto_trainer.html | 196 kB | | e1f5dfd9 |
| liger_kernel_integration.html | 4.16 kB | | 922e5074 |
| logging.html | 16.5 kB | | c83e550c |
| models.html | 124 kB | | 5986dc8c |
| multi_adapter_rl.html | 21.9 kB | | 4cd8787e |
| nash_md_trainer.html | 101 kB | | ff578156 |
| objects.inv | 2.26 kB | | 00eaf514 |
| online_dpo_trainer.html | 147 kB | | a6c51cee |
| orpo_trainer.html | 177 kB | | fc848640 |
| others.html | 25.3 kB | | 32c9c3f7 |
| peft_integration.html | 35.8 kB | | 76df1d47 |
| ppo_trainer.html | 121 kB | | 12846805 |
| prm_trainer.html | 127 kB | | 91de6d08 |
| quickstart.html | 17.3 kB | | c88dcb7d |
| reducing_memory_usage.html | 24.5 kB | | c08f3faa |
| reward_trainer.html | 85.4 kB | | d988d50c |
| rloo_trainer.html | 121 kB | | f23dce9d |
| script_utils.html | 55.9 kB | | 196b8fd6 |
| sentiment_tuning.html | 11.1 kB | | a4d95470 |
| sft_trainer.html | 262 kB | | 3c11e7a2 |
| speeding_up_training.html | 11.1 kB | | 082e7f6b |
| training_vlm_sft.html | 68.7 kB | | 490f8870 |
| unsloth_integration.html | 4.12 kB | | ef7afc22 |
| use_model.html | 15.1 kB | | b8aa57ae |
| using_llama_models.html | 30.3 kB | | 38a3e05d |
| vllm_integration.html | 11.4 kB | | 732f3a67 |
| xpo_trainer.html | 101 kB | | 82472b6e |