| _app | | | 133 items |
| _toctree.yml | 3.21 kB | | ae39baa5 |
| bco_trainer.html | 131 kB | | 2c63aab2 |
| bco_trainer.md | 13.8 kB | | aaab4e1c |
| bema_for_reference_model.html | 89.7 kB | | e500709f |
| bema_for_reference_model.md | 7.42 kB | | d32d5ace |
| callbacks.html | 101 kB | | 0a1fa0d1 |
| callbacks.md | 8.14 kB | | 94499353 |
| chat_template_utils.html | 69 kB | | 33f4aa4e |
| chat_template_utils.md | 7.22 kB | | da8f4f26 |
| clis.html | 53.4 kB | | ad8d6826 |
| clis.md | 12.8 kB | | 1b7ac500 |
| community_tutorials.html | 31 kB | | ee5d6308 |
| community_tutorials.md | 10.9 kB | | 8d09f9a2 |
| cpo_trainer.html | 145 kB | | 1f69f9bf |
| cpo_trainer.md | 22.6 kB | | fd2d3dd2 |
| customization.html | 37.4 kB | | 8f798ea7 |
| customization.md | 4.9 kB | | 7f8be4d1 |
| data_utils.html | 177 kB | | 02fceb6f |
| data_utils.md | 18.9 kB | | 9dd8821d |
| dataset_formats.html | 219 kB | | 360a0ea3 |
| dataset_formats.md | 41.2 kB | | fe70dea4 |
| deepspeed_integration.html | 15.8 kB | | 910df326 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distributing_training.html | 80.8 kB | | 61ad3628 |
| distributing_training.md | 18.7 kB | | 374f883e |
| dpo_trainer.html | 243 kB | | 268fa818 |
| dpo_trainer.md | 35.2 kB | | 2ae584b6 |
| example_overview.html | 36.4 kB | | 91a6af6d |
| example_overview.md | 16.8 kB | | c2633a4f |
| experimental_overview.html | 10.8 kB | | b06b8958 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 82.4 kB | | 6b9048e8 |
| gfpo.md | 5.06 kB | | 89c79783 |
| gkd_trainer.html | 116 kB | | 1adeeb46 |
| gkd_trainer.md | 13.7 kB | | e5c22680 |
| gold_trainer.html | 150 kB | | 9002b217 |
| gold_trainer.md | 15.4 kB | | 85ab9750 |
| grpo_trainer.html | 530 kB | | ba28823e |
| grpo_trainer.md | 48.8 kB | | d54596e7 |
| grpo_with_replay_buffer.html | 87.6 kB | | 6ea60b44 |
| grpo_with_replay_buffer.md | 5.99 kB | | 20001a5a |
| gspo_token.html | 49 kB | | b750c5d8 |
| gspo_token.md | 4.1 kB | | fcc73d02 |
| index.html | 28.6 kB | | 054c84cf |
| index.md | 3.68 kB | | a08ded5f |
| installation.html | 13.9 kB | | cd850697 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 2c70435d |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| judges.html | 119 kB | | 1e1d38db |
| judges.md | 15 kB | | 6f01596c |
| kernels_hub.html | 26.8 kB | | 090dcdcf |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 136 kB | | 4bdb4835 |
| kto_trainer.md | 18.8 kB | | 020f62a9 |
| liger_kernel_integration.html | 15 kB | | 2aca7b9f |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 821 kB | | ac927de0 |
| llms.txt | 4.86 kB | | 7e6c1bed |
| lora_without_regret.html | 45.1 kB | | cefd07d9 |
| lora_without_regret.md | 14.5 kB | | 1d6262a4 |
| merge_model_callback.html | 17.8 kB | | a77ecdbb |
| merge_model_callback.md | 1.19 kB | | 53fdb393 |
| minillm_trainer.html | 177 kB | | 61309569 |
| minillm_trainer.md | 16.3 kB | | 7c9ccfd7 |
| model_utils.html | 40.6 kB | | 7d59c8a2 |
| model_utils.md | 3.42 kB | | 660e483c |
| nash_md_trainer.html | 127 kB | | 97f1ed5e |
| nash_md_trainer.md | 16.5 kB | | 2478930c |
| objects.inv | 2.58 kB | | 442a25ac |
| online_dpo_trainer.html | 190 kB | | 6caa482d |
| online_dpo_trainer.md | 25.2 kB | | eaba196a |
| openenv.html | 87.8 kB | | cff1e342 |
| openenv.md | 25.2 kB | | b5c69d14 |
| orpo_trainer.html | 127 kB | | f5030c8c |
| orpo_trainer.md | 17.2 kB | | 3cf3e63c |
| others.html | 29.7 kB | | 445b6653 |
| others.md | 2.18 kB | | 8c16f6b8 |
| paper_index.html | 503 kB | | debf6b49 |
| paper_index.md | 31.8 kB | | 93e71e47 |
| papo_trainer.html | 109 kB | | 65831b11 |
| papo_trainer.md | 8.65 kB | | 5615b325 |
| peft_integration.html | 131 kB | | f7f505e9 |
| peft_integration.md | 23.8 kB | | 575f6bb6 |
| ppo_trainer.html | 278 kB | | 6d2a5eb4 |
| ppo_trainer.md | 41.3 kB | | 5fea7b74 |
| prm_trainer.html | 116 kB | | b3f03ca0 |
| prm_trainer.md | 13.5 kB | | 81464639 |
| ptt_integration.html | 29.3 kB | | 671453c3 |
| ptt_integration.md | 4.22 kB | | 4ea19a56 |
| quickstart.html | 37.7 kB | | 4ba5a71b |
| quickstart.md | 3.36 kB | | 1a8bc789 |
| rapidfire_integration.html | 81.2 kB | | 03688c97 |
| rapidfire_integration.md | 12.8 kB | | 33fdfe4a |
| reducing_memory_usage.html | 52.8 kB | | 95c3c0d5 |
| reducing_memory_usage.md | 11.7 kB | | b80ef4e4 |
| reward_trainer.html | 192 kB | | fbf34886 |
| reward_trainer.md | 23.5 kB | | 497ba7de |
|