| _app | | | 33,235 items |
| _toctree.yml | 3.44 kB | | 84481523 |
| a2po_trainer.html | 101 kB | | 7ee2a050 |
| a2po_trainer.md | 16.4 kB | | 4f9b31b6 |
| alignprop_trainer.html | 100 kB | | 465c2c3a |
| async_grpo_trainer.html | 157 kB | | 37baad5b |
| async_grpo_trainer.md | 33.1 kB | | 3a0de330 |
| bco_trainer.html | 133 kB | | 138ba151 |
| bco_trainer.md | 21.5 kB | | 5fd5beb7 |
| bema_for_reference_model.html | 91.4 kB | | 3ae79cfb |
| bema_for_reference_model.md | 7.1 kB | | 8d783cd5 |
| best_of_n.html | 47.2 kB | | ac540ed1 |
| best_of_n.md | 7.29 kB | | c01be246 |
| callbacks.html | 97.3 kB | | 94455691 |
| callbacks.md | 8.8 kB | | 4711a5ba |
| chat_template_utils.html | 45.9 kB | | 52cd1229 |
| chat_template_utils.md | 7.02 kB | | 0354076f |
| chat_templates.html | 62.5 kB | | 7c9ee523 |
| chat_templates.md | 13.1 kB | | 2550f92f |
| clis.html | 53.6 kB | | 9aa70ba5 |
| clis.md | 12.8 kB | | 99d17a07 |
| community_tutorials.html | 30.7 kB | | b5befee5 |
| community_tutorials.md | 10.9 kB | | 7df211b2 |
| cpo_trainer.html | 144 kB | | bf3a3ebb |
| cpo_trainer.md | 29.6 kB | | 1a6fc5c9 |
| customization.html | 30.6 kB | | d1d121e5 |
| customization.md | 4.07 kB | | 65b8bd92 |
| data_utils.html | 61.6 kB | | 28277d6b |
| data_utils.md | 7.26 kB | | 16c82264 |
| dataset_formats.html | 220 kB | | de8da9a4 |
| dataset_formats.md | 42.9 kB | | 98a6d1d0 |
| ddpo_trainer.html | 144 kB | | 9ca7c90c |
| deepspeed_integration.html | 15.5 kB | | fc4ba649 |
| deepspeed_integration.md | 1.52 kB | | e5b0fad5 |
| detoxifying_a_lm.html | 48.6 kB | | 764a2b7c |
| detoxifying_a_lm.md | 12.6 kB | | c49fb8ba |
| distillation_trainer.html | 150 kB | | 7e17c21b |
| distillation_trainer.md | 23.5 kB | | f7e3bee4 |
| distributing_training.html | 94.8 kB | | b4c74cea |
| distributing_training.md | 21 kB | | 2b14cde4 |
| dpo_trainer.html | 237 kB | | c3db57ac |
| dpo_trainer.md | 46 kB | | df10fa1c |
| example_overview.html | 45.9 kB | | e17ebc80 |
| example_overview.md | 22.8 kB | | 80dcdf42 |
| experimental.html | 40.6 kB | | 028ef10c |
| experimental.md | 6.53 kB | | 7e69ae86 |
| experimental_overview.html | 10.4 kB | | 5a46869f |
| experimental_overview.md | 1.62 kB | | 45d90cc6 |
| extras.html | 14 kB | | e3292031 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 86.5 kB | | 4eac1b7b |
| gfpo.md | 11.2 kB | | 9b5d0477 |
| gkd_trainer.html | 118 kB | | 51c4d9ce |
| gkd_trainer.md | 20.8 kB | | fb1d5607 |
| gmpo.html | 88.9 kB | | d0ed3459 |
| gmpo.md | 13.4 kB | | 312c319c |
| gold_trainer.html | 191 kB | | a224753d |
| gold_trainer.md | 32.5 kB | | 3679af3f |
| grpo_trainer.html | 633 kB | | fcf500e2 |
| grpo_trainer.md | 114 kB | | c4f5690f |
| grpo_with_replay_buffer.html | 91.9 kB | | 94447ab6 |
| grpo_with_replay_buffer.md | 13.1 kB | | 0089d17b |
| gspo_token.html | 49.6 kB | | 51532f40 |
| gspo_token.md | 5.28 kB | | e2535a73 |
| harbor.html | 76.3 kB | | 735a68c0 |
| harbor.md | 13.8 kB | | dcf95159 |
| how_to_train.html | 22.9 kB | | d23974d0 |
| how_to_train.md | 6.9 kB | | cd72449d |
| index.html | 29.1 kB | | 8ad18ce2 |
| index.md | 3.92 kB | | 8c3da09b |
| installation.html | 13.7 kB | | f7012b70 |
| installation.md | 721 Bytes | | 93a212e0 |
| iterative_sft_trainer.html | 117 kB | | b4192557 |
| jobs_training.html | 32.7 kB | | 26d80f01 |
| jobs_training.md | 6.5 kB | | 1912e3c9 |
| judges.html | 122 kB | | 9d502a74 |
| judges.md | 15.8 kB | | c9fdab04 |
| kernels_hub.html | 26.2 kB | | f803a6b3 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 219 kB | | 1b224005 |
| kto_trainer.md | 41.9 kB | | 8e958160 |
| learning_tools.html | 44.9 kB | | 4651e1bf |
| liger_kernel_integration.html | 14.8 kB | | 11a76333 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 1.34 MB | | 9abbc01c |
| llms.txt | 5.09 kB | | 55a1c4ad |
| logging.html | 28.1 kB | | 47a63187 |
| logging.md | 9.55 kB | | eba13e89 |
| lora_tuning_peft.html | 35.7 kB | | 93b2ef0b |
| lora_without_regret.html | 44.1 kB | | 597a0d3b |
| lora_without_regret.md | 14.3 kB | | e31f56a0 |
| merge_model_callback.html | 17.5 kB | | fa9eeedc |
| merge_model_callback.md | 1.39 kB | | 72cef9b0 |
| minillm.html | 183 kB | | ab9c1ad9 |
| minillm.md | 16.4 kB | | 22f4793c |
| minillm_trainer.html | 181 kB | | 36f9cde0 |
| minillm_trainer.md | 25.4 kB | | e1d7a74e |
| model_utils.html | 31 kB | | 516c91b0 |
| model_utils.md | 2.73 kB | | 0edd2ba1 |
| models.html | 128 kB | | 6b7dd0bf |
|