| _app | | | 158 items |
| _toctree.yml | 3.38 kB | | 9da8f3eb |
| async_grpo_trainer.html | 108 kB | | ffd14bb8 |
| async_grpo_trainer.md | 12.3 kB | | ccfce5f0 |
| bco_trainer.html | 130 kB | | cce5349d |
| bco_trainer.md | 14.1 kB | | a4a68d76 |
| bema_for_reference_model.html | 90 kB | | 62a1a64e |
| bema_for_reference_model.md | 7.18 kB | | 23199680 |
| callbacks.html | 95.8 kB | | 4e887f3f |
| callbacks.md | 7.88 kB | | fd980b20 |
| chat_template_utils.html | 46.2 kB | | 6f5f4ae7 |
| chat_template_utils.md | 5.76 kB | | 324321f7 |
| chat_templates.html | 33.5 kB | | ac3b4253 |
| chat_templates.md | 6.03 kB | | c10124ce |
| clis.html | 53.4 kB | | 46b26ae2 |
| clis.md | 12.8 kB | | e0986ca7 |
| community_tutorials.html | 31 kB | | 28049ba6 |
| community_tutorials.md | 11 kB | | fef25108 |
| cpo_trainer.html | 144 kB | | 480beb9d |
| cpo_trainer.md | 23 kB | | 9606aafe |
| customization.html | 31 kB | | 405acf4d |
| customization.md | 4.08 kB | | c2741a0b |
| data_utils.html | 62.7 kB | | 82bc3cbf |
| data_utils.md | 6.87 kB | | 16373e34 |
| dataset_formats.html | 223 kB | | b1998668 |
| dataset_formats.md | 40.2 kB | | 6e8d190c |
| deepspeed_integration.html | 15.8 kB | | b923ffe9 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 161 kB | | e8ca934f |
| distillation_trainer.md | 12.3 kB | | 16ea2b6b |
| distributing_training.html | 96.5 kB | | 72ba8c87 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 233 kB | | 29f0d7aa |
| dpo_trainer.md | 30.8 kB | | 434909f2 |
| example_overview.html | 42.8 kB | | f2d2bdac |
| example_overview.md | 19.7 kB | | bc77ef08 |
| experimental_overview.html | 10.8 kB | | 79cd6cbd |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 85 kB | | db91038e |
| gfpo.md | 5.24 kB | | cd9e1945 |
| gkd_trainer.html | 119 kB | | f5c1e1ff |
| gkd_trainer.md | 14.1 kB | | a345f3e7 |
| gold_trainer.html | 166 kB | | 8a46412c |
| gold_trainer.md | 18.1 kB | | 6a7aac28 |
| grpo_trainer.html | 561 kB | | 2659ab21 |
| grpo_trainer.md | 55.8 kB | | 15407518 |
| grpo_with_replay_buffer.html | 90.3 kB | | 2d0b423b |
| grpo_with_replay_buffer.md | 6.16 kB | | a9adec14 |
| gspo_token.html | 50.2 kB | | 0eb5d301 |
| gspo_token.md | 4.27 kB | | b2dd8f88 |
| index.html | 29 kB | | e8256682 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 687ed4da |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | d4a461ab |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | 8d186580 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 138 kB | | 01068422 |
| kto_trainer.md | 18.3 kB | | 5e50158a |
| liger_kernel_integration.html | 15 kB | | 8f1f0289 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 868 kB | | 28cd1db1 |
| llms.txt | 5.15 kB | | 2c85ab49 |
| lora_without_regret.html | 45 kB | | 9e8688b4 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | b76996f9 |
| merge_model_callback.md | 1.19 kB | | b7c3a053 |
| minillm_trainer.html | 180 kB | | f4f0e120 |
| minillm_trainer.md | 16.4 kB | | d9c83070 |
| nash_md_trainer.html | 125 kB | | 8845dc17 |
| nash_md_trainer.md | 16.3 kB | | e257afa7 |
| nemo_gym.html | 58.5 kB | | 168b5ed6 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.45 kB | | d5ed6d0c |
| online_dpo_trainer.html | 180 kB | | 19737c73 |
| online_dpo_trainer.md | 23.1 kB | | 6b617073 |
| openenv.html | 114 kB | | e5f9ac3c |
| openenv.md | 27.8 kB | | b7b225a7 |
| orpo_trainer.html | 127 kB | | a95a74ae |
| orpo_trainer.md | 17.7 kB | | c2781ac1 |
| paper_index.html | 742 kB | | 7d452e7f |
| paper_index.md | 19.1 kB | | e7fea57d |
| papo_trainer.html | 112 kB | | fa7a7c2b |
| papo_trainer.md | 8.82 kB | | ee77d8da |
| peft_integration.html | 131 kB | | 548db62a |
| peft_integration.md | 23.9 kB | | 7f5c2e26 |
| ppo_trainer.html | 279 kB | | 725c5e5a |
| ppo_trainer.md | 41.4 kB | | 542b4c3d |
| prm_trainer.html | 118 kB | | 78def7ef |
| prm_trainer.md | 13.9 kB | | efe86f78 |
| ptt_integration.html | 29.3 kB | | a0bbfc6e |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 07846f02 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 95.4 kB | | 270db3d2 |
| rapidfire_integration.md | 17.7 kB | | 08fed5af |
| reducing_memory_usage.html | 52.4 kB | | e7de584f |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
|