| _app | | | 250 items |
| _toctree.yml | 2.85 kB | | 4c7f3dc2 |
| alignprop_trainer.html | 25 kB | | 58004231 |
| bco_trainer.html | 179 kB | | b795f63f |
| best_of_n.html | 15.7 kB | | e1401207 |
| callbacks.html | 57.2 kB | | 96bdd86e |
| clis.html | 35 kB | | 4ea52705 |
| community_tutorials.html | 17 kB | | aa94a6ef |
| cpo_trainer.html | 185 kB | | 94132425 |
| customization.html | 23.9 kB | | bc4e722f |
| data_utils.html | 133 kB | | e1d453ac |
| dataset_formats.html | 221 kB | | 203f1914 |
| ddpo_trainer.html | 144 kB | | 1570de28 |
| deepspeed_integration.html | 13.8 kB | | 8c52fe37 |
| detoxifying_a_lm.html | 46.3 kB | | 043b3ac3 |
| distributing_training.html | 15.8 kB | | 964f438f |
| dpo_trainer.html | 295 kB | | ed23fe29 |
| example_overview.html | 27.1 kB | | 287d7355 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gkd_trainer.html | 93.3 kB | | 311fd629 |
| grpo_trainer.html | 389 kB | | b3cbed26 |
| how_to_train.html | 20.7 kB | | 83b43ddf |
| index.html | 13.6 kB | | 89b56a29 |
| installation.html | 11.5 kB | | 0ea97423 |
| iterative_sft_trainer.html | 116 kB | | 99d07786 |
| judges.html | 117 kB | | a7c7f2b8 |
| kto_trainer.html | 196 kB | | 282942ac |
| liger_kernel_integration.html | 4.18 kB | | 09455f41 |
| logging.html | 21.2 kB | | 4f17b4fa |
| model_utils.html | 36.2 kB | | 27785f81 |
| models.html | 124 kB | | 7218ac97 |
| multi_adapter_rl.html | 21.9 kB | | f26d8644 |
| nash_md_trainer.html | 102 kB | | 7e16b695 |
| objects.inv | 2.33 kB | | 858cc6d1 |
| online_dpo_trainer.html | 147 kB | | fb2ef1da |
| orpo_trainer.html | 177 kB | | f29c5d00 |
| others.html | 25.3 kB | | 548aae66 |
| peft_integration.html | 35.8 kB | | b227f93d |
| ppo_trainer.html | 122 kB | | 6b64043b |
| prm_trainer.html | 127 kB | | 7db98a91 |
| quickstart.html | 17.3 kB | | cda6c1ed |
| reducing_memory_usage.html | 35.6 kB | | de1dc9dd |
| reward_trainer.html | 86.4 kB | | cf26790e |
| rewards.html | 18.1 kB | | 92efcee9 |
| rloo_trainer.html | 122 kB | | 855ce852 |
| script_utils.html | 57.8 kB | | 12fdc00d |
| sentiment_tuning.html | 11.1 kB | | 8bbc80bd |
| sft_trainer.html | 273 kB | | 66edf222 |
| speeding_up_training.html | 11.1 kB | | 9cfd314f |
| training_vlm_sft.html | 68.5 kB | | 43a007ff |
| unsloth_integration.html | 4.14 kB | | 14e9ad99 |
| use_model.html | 15.1 kB | | fd7ecacb |
| using_llama_models.html | 30.3 kB | | 09e4358a |
| vllm_integration.html | 46.1 kB | | 26ec24e6 |
| xpo_trainer.html | 102 kB | | 86a4a451 |