| _app | | | 339 items |
| _toctree.yml | 3.25 kB | | dc2455d5 |
| bco_trainer.html | 128 kB | | 5a331e6d |
| bco_trainer.md | 13.5 kB | | 78ac9d2d |
| bema_for_reference_model.html | 89.7 kB | | e39ad35c |
| bema_for_reference_model.md | 7.42 kB | | b6862672 |
| callbacks.html | 101 kB | | 546312b4 |
| callbacks.md | 8.14 kB | | fd2d7c11 |
| chat_template_utils.html | 69 kB | | d0513e5c |
| chat_template_utils.md | 7.22 kB | | 0ad40dba |
| clis.html | 53.4 kB | | 21ed2369 |
| clis.md | 12.8 kB | | efdee7c0 |
| community_tutorials.html | 31 kB | | 78f549b9 |
| community_tutorials.md | 11 kB | | 874e0c2f |
| cpo_trainer.html | 142 kB | | 4b66b266 |
| cpo_trainer.md | 22.3 kB | | 24b20a98 |
| customization.html | 37.4 kB | | bb9b1b92 |
| customization.md | 4.91 kB | | b484a925 |
| data_utils.html | 177 kB | | f5a90a78 |
| data_utils.md | 18.9 kB | | 41a001a7 |
| dataset_formats.html | 219 kB | | 63cc3d6b |
| dataset_formats.md | 41.2 kB | | 5df1f64e |
| deepspeed_integration.html | 15.8 kB | | fe73ea66 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distributing_training.html | 80.8 kB | | a567473c |
| distributing_training.md | 18.7 kB | | 374f883e |
| dpo_trainer.html | 243 kB | | a604bf0a |
| dpo_trainer.md | 35.3 kB | | e4e921a9 |
| example_overview.html | 37 kB | | c4873207 |
| example_overview.md | 17.3 kB | | 9ec1456b |
| experimental_overview.html | 10.8 kB | | c866a532 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 82.4 kB | | e5ec8c2d |
| gfpo.md | 5.06 kB | | 7d2c5021 |
| gkd_trainer.html | 116 kB | | e45a1a82 |
| gkd_trainer.md | 13.7 kB | | 0999952f |
| gold_trainer.html | 150 kB | | d78f5354 |
| gold_trainer.md | 15.4 kB | | ae903f38 |
| grpo_trainer.html | 530 kB | | c09324e4 |
| grpo_trainer.md | 48.8 kB | | 4193b9d6 |
| grpo_with_replay_buffer.html | 87.6 kB | | 8a0a47e6 |
| grpo_with_replay_buffer.md | 5.99 kB | | 6058a46f |
| gspo_token.html | 49 kB | | c12fa376 |
| gspo_token.md | 4.1 kB | | 50372fb6 |
| index.html | 28.6 kB | | cfafb491 |
| index.md | 3.68 kB | | a08ded5f |
| installation.html | 13.9 kB | | 682201cc |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 37b9663b |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| judges.html | 119 kB | | f31f29e3 |
| judges.md | 15 kB | | 42fcf862 |
| kernels_hub.html | 26.8 kB | | bf424e3d |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 136 kB | | 76dcbd53 |
| kto_trainer.md | 18.8 kB | | f31884a5 |
| liger_kernel_integration.html | 15 kB | | d6950065 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 832 kB | | 643a468c |
| llms.txt | 4.93 kB | | 188cbaff |
| lora_without_regret.html | 45.1 kB | | b3be4df4 |
| lora_without_regret.md | 14.5 kB | | 1d6262a4 |
| merge_model_callback.html | 17.8 kB | | b6644a61 |
| merge_model_callback.md | 1.19 kB | | b973bafb |
| minillm_trainer.html | 177 kB | | 41654446 |
| minillm_trainer.md | 16.3 kB | | 4152ed41 |
| model_utils.html | 40.6 kB | | c7ccc2b4 |
| model_utils.md | 3.42 kB | | c46fb1e2 |
| nash_md_trainer.html | 127 kB | | c70899a1 |
| nash_md_trainer.md | 16.5 kB | | e7f5b325 |
| nemo_gym.html | 58.5 kB | | d3b79874 |
| nemo_gym.md | 10.4 kB | | 0fcf2e53 |
| objects.inv | 2.61 kB | | 4140c478 |
| online_dpo_trainer.html | 190 kB | | 5617cc88 |
| online_dpo_trainer.md | 25.2 kB | | 765c2045 |
| openenv.html | 89.7 kB | | 57ad7e60 |
| openenv.md | 25.6 kB | | 310aec43 |
| orpo_trainer.html | 125 kB | | aabb470c |
| orpo_trainer.md | 17.1 kB | | 140e5762 |
| others.html | 29.8 kB | | 6a68a49c |
| others.md | 2.29 kB | | fd1cafdd |
| paper_index.html | 503 kB | | 6eb43187 |
| paper_index.md | 31.9 kB | | cd1a529c |
| papo_trainer.html | 109 kB | | 32cb23f1 |
| papo_trainer.md | 8.65 kB | | e45a492d |
| peft_integration.html | 131 kB | | f6f78b74 |
| peft_integration.md | 23.8 kB | | 575f6bb6 |
| ppo_trainer.html | 275 kB | | ff6531d6 |
| ppo_trainer.md | 41.1 kB | | e001c4f4 |
| prm_trainer.html | 115 kB | | 6bad876e |
| prm_trainer.md | 13.4 kB | | f07316d8 |
| ptt_integration.html | 29.3 kB | | 009d5b43 |
| ptt_integration.md | 4.22 kB | | 4ea19a56 |
| quickstart.html | 37.7 kB | | 669cf037 |
| quickstart.md | 3.36 kB | | 1a8bc789 |
| rapidfire_integration.html | 81.2 kB | | d0e32d60 |
| rapidfire_integration.md | 12.8 kB | | 33fdfe4a |
| reducing_memory_usage.html | 52.8 kB | | 8634dadf |
| reducing_memory_usage.md | 11.7 kB | | e9f7c77d |
|