| _app | | | 226 items |
| _toctree.yml | 2.85 kB | | 4c7f3dc2 |
| alignprop_trainer.html | 25 kB | | 8ca8310f |
| bco_trainer.html | 178 kB | | 6071921a |
| best_of_n.html | 15.7 kB | | 5be0006a |
| callbacks.html | 57.2 kB | | 935e6feb |
| clis.html | 35 kB | | cb636609 |
| community_tutorials.html | 16.3 kB | | 11cd9457 |
| cpo_trainer.html | 184 kB | | d24f5cd5 |
| customization.html | 23.9 kB | | 54532fe6 |
| data_utils.html | 133 kB | | 88e601ba |
| dataset_formats.html | 221 kB | | e1f3b56e |
| ddpo_trainer.html | 144 kB | | c7c4b74b |
| deepspeed_integration.html | 13.8 kB | | 8e7be97a |
| detoxifying_a_lm.html | 46.3 kB | | 9cc0426c |
| distributing_training.html | 15.8 kB | | e702a739 |
| dpo_trainer.html | 294 kB | | 936676f8 |
| example_overview.html | 27.1 kB | | 4321039f |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gkd_trainer.html | 112 kB | | 0b767a1d |
| grpo_trainer.html | 389 kB | | f87f19c7 |
| how_to_train.html | 20.7 kB | | f802dd2e |
| index.html | 13.6 kB | | da0d4e9a |
| installation.html | 11.5 kB | | 118d6112 |
| iterative_sft_trainer.html | 115 kB | | db5a1845 |
| judges.html | 117 kB | | 4d53fdda |
| kto_trainer.html | 195 kB | | a182d783 |
| liger_kernel_integration.html | 4.18 kB | | 417b02e9 |
| logging.html | 21.2 kB | | c53b6c54 |
| model_utils.html | 36.2 kB | | eb826ca9 |
| models.html | 124 kB | | 703bde5b |
| multi_adapter_rl.html | 21.9 kB | | 36a5b23e |
| nash_md_trainer.html | 101 kB | | fbcfce34 |
| objects.inv | 2.33 kB | | 26df3982 |
| online_dpo_trainer.html | 146 kB | | 4753bf71 |
| orpo_trainer.html | 176 kB | | 12ef9d86 |
| others.html | 25.3 kB | | 8a13cbfc |
| peft_integration.html | 35.8 kB | | d2be7532 |
| ppo_trainer.html | 122 kB | | 41bac74d |
| prm_trainer.html | 126 kB | | a36e5e93 |
| quickstart.html | 17.3 kB | | 66515339 |
| reducing_memory_usage.html | 35.6 kB | | 0c8e9974 |
| reward_trainer.html | 86.4 kB | | 6286274e |
| rewards.html | 18.1 kB | | e3f15a73 |
| rloo_trainer.html | 122 kB | | 3799a309 |
| script_utils.html | 57.8 kB | | 6d9f3231 |
| sentiment_tuning.html | 11.1 kB | | 6ea03d53 |
| sft_trainer.html | 273 kB | | 2d7e1366 |
| speeding_up_training.html | 11.1 kB | | 5abfbe8e |
| training_vlm_sft.html | 68.5 kB | | 5c0a21f2 |
| unsloth_integration.html | 4.14 kB | | 660d25f3 |
| use_model.html | 15.1 kB | | 74ded010 |
| using_llama_models.html | 30.3 kB | | 876d9e68 |
| vllm_integration.html | 46.1 kB | | 12a51c0c |
| xpo_trainer.html | 101 kB | | 792bb4bf |