| _app | | | 387 items |
| _toctree.yml | 3.57 kB | | 4caf8fc8 |
| a2po_trainer.html | 102 kB | | 4994c7de |
| a2po_trainer.md | 14.1 kB | | e5fc6934 |
| async_grpo_trainer.html | 143 kB | | fba41f1d |
| async_grpo_trainer.md | 25.2 kB | | 73a8744f |
| bco_trainer.html | 133 kB | | 2b9e8563 |
| bco_trainer.md | 18.2 kB | | c4f1d2e9 |
| bema_for_reference_model.html | 88.6 kB | | 11d7a383 |
| bema_for_reference_model.md | 5.55 kB | | 4202d9ff |
| callbacks.html | 94.5 kB | | b7e562b3 |
| callbacks.md | 7.21 kB | | 9c2a60ac |
| chat_template_utils.html | 45.9 kB | | eee3e987 |
| chat_template_utils.md | 5.8 kB | | 956d17e2 |
| chat_templates.html | 60.6 kB | | 99c2bac8 |
| chat_templates.md | 12.5 kB | | 0c123c8d |
| clis.html | 53.7 kB | | 4ddf3827 |
| clis.md | 12.8 kB | | e6db15c7 |
| community_tutorials.html | 30.8 kB | | b80bca3c |
| community_tutorials.md | 11 kB | | f2dd5755 |
| cpo_trainer.html | 144 kB | | 8fdb9107 |
| cpo_trainer.md | 26.6 kB | | a7accbd8 |
| customization.html | 30.7 kB | | 2408bfcc |
| customization.md | 4.08 kB | | fafca3dd |
| data_utils.html | 61.7 kB | | 37c7b790 |
| data_utils.md | 6.34 kB | | 6963381f |
| dataset_formats.html | 221 kB | | 7e6985e0 |
| dataset_formats.md | 43 kB | | 88d4c539 |
| deepspeed_integration.html | 15.5 kB | | c425757d |
| deepspeed_integration.md | 1.52 kB | | e5b0fad5 |
| distillation_trainer.html | 161 kB | | e7bc1ef0 |
| distillation_trainer.md | 23.6 kB | | 492bb2d9 |
| distributing_training.html | 94.9 kB | | 2f73ae26 |
| distributing_training.md | 21 kB | | 2b14cde4 |
| dpo_trainer.html | 235 kB | | 4e80bb3e |
| dpo_trainer.md | 42.8 kB | | 5ed65ec3 |
| example_overview.html | 45.6 kB | | 13aa81d6 |
| example_overview.md | 22.5 kB | | ff07d564 |
| experimental_overview.html | 10.5 kB | | 9fc7d2f6 |
| experimental_overview.md | 1.62 kB | | 45d90cc6 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 86.5 kB | | c72dc14e |
| gfpo.md | 11.2 kB | | 9b5d0477 |
| gkd_trainer.html | 118 kB | | 51ccc717 |
| gkd_trainer.md | 18 kB | | 55070689 |
| gmpo.html | 88.8 kB | | 1c8a60a3 |
| gmpo.md | 12.7 kB | | 389f9fd4 |
| gold_trainer.html | 192 kB | | ef66319b |
| gold_trainer.md | 30.7 kB | | 75f8bf9a |
| grpo_trainer.html | 604 kB | | 17b1635a |
| grpo_trainer.md | 102 kB | | b0fcdead |
| grpo_with_replay_buffer.html | 91.8 kB | | bc690fef |
| grpo_with_replay_buffer.md | 11.5 kB | | 952f83c9 |
| gspo_token.html | 49.4 kB | | e92c043f |
| gspo_token.md | 2.71 kB | | ed4cf9c1 |
| harbor.html | 76.4 kB | | 09576791 |
| harbor.md | 12.7 kB | | 93ed01b1 |
| index.html | 29.1 kB | | 4f123ba8 |
| index.md | 3.9 kB | | ce02d059 |
| installation.html | 13.7 kB | | 0b9d7f7f |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.7 kB | | 28e93e42 |
| jobs_training.md | 6.45 kB | | 38e66142 |
| judges.html | 122 kB | | dc32f9cf |
| judges.md | 15.8 kB | | ee25f07c |
| kernels_hub.html | 26.3 kB | | b9207c49 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 163 kB | | 8a60ce01 |
| kto_trainer.md | 25.6 kB | | 6bbfecf8 |
| liger_kernel_integration.html | 14.8 kB | | a1ecad1f |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 1.26 MB | | 81237ef9 |
| llms.txt | 5.51 kB | | c148e637 |
| lora_without_regret.html | 44.1 kB | | 33b0cef8 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.6 kB | | cfaaa54a |
| merge_model_callback.md | 991 Bytes | | ba2b22af |
| minillm_trainer.html | 181 kB | | dd871aa5 |
| minillm_trainer.md | 23.7 kB | | 919609b9 |
| nash_md_trainer.html | 124 kB | | 497d01bf |
| nash_md_trainer.md | 20.4 kB | | 192a1c0f |
| nemo_gym.html | 58.5 kB | | bce4906c |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.69 kB | | 7efcdf6a |
| online_dpo_trainer.html | 180 kB | | bbb9ec68 |
| online_dpo_trainer.md | 33.3 kB | | d0fb3bf9 |
| openenv.html | 116 kB | | 86de5ea6 |
| openenv.md | 28.2 kB | | 9283913d |
| openreward.html | 70.4 kB | | 6a10c657 |
| openreward.md | 11.4 kB | | b90b3b85 |
| orpo_trainer.html | 127 kB | | 1a24b3c5 |
| orpo_trainer.md | 21 kB | | 60a1d372 |
| paper_index.html | 809 kB | | 701aee0a |
| paper_index.md | 91.1 kB | | 7e86beb1 |
| papo_trainer.html | 114 kB | | fcf892c3 |
| papo_trainer.md | 15.9 kB | | e38199c2 |
| peft_integration.html | 130 kB | | 1f89a14e |
| peft_integration.md | 24.2 kB | | 806abd05 |
| ppo_trainer.html | 275 kB | | b840c776 |
| ppo_trainer.md | 42.6 kB | | 63cbe84f |
|