| _app | | | 1,373 items |
| _toctree.yml | 3.22 kB | | ca36b740 |
| async_grpo_trainer.html | 108 kB | | 69be5e6d |
| async_grpo_trainer.md | 12.3 kB | | 67c183d2 |
| bco_trainer.html | 131 kB | | 848212c8 |
| bco_trainer.md | 14.4 kB | | b8630203 |
| bema_for_reference_model.html | 90 kB | | 5fc50d8e |
| bema_for_reference_model.md | 7.18 kB | | d5dfd79c |
| callbacks.html | 95.8 kB | | 2b1fcde9 |
| callbacks.md | 7.88 kB | | 17ab3487 |
| chat_template_utils.html | 43.9 kB | | 31be55fe |
| chat_template_utils.md | 4.65 kB | | de272331 |
| clis.html | 53.4 kB | | cf06d06c |
| clis.md | 12.8 kB | | d75cb80b |
| community_tutorials.html | 31 kB | | 3a6dfb30 |
| community_tutorials.md | 11 kB | | 90194772 |
| cpo_trainer.html | 146 kB | | f11615d6 |
| cpo_trainer.md | 23.2 kB | | 333b9950 |
| customization.html | 31 kB | | 40cf2353 |
| customization.md | 4.08 kB | | 13867bad |
| data_utils.html | 62.9 kB | | a583192b |
| data_utils.md | 6.32 kB | | 59e52436 |
| dataset_formats.html | 223 kB | | 1e250767 |
| dataset_formats.md | 40.2 kB | | 879c2039 |
| deepspeed_integration.html | 15.8 kB | | f734b976 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distributing_training.html | 96.5 kB | | b356192f |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 231 kB | | 5eadb3d0 |
| dpo_trainer.md | 30.6 kB | | f7a114d4 |
| example_overview.html | 39.6 kB | | 155b2a18 |
| example_overview.md | 19.5 kB | | 47854ae4 |
| experimental_overview.html | 10.8 kB | | b827369c |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | f73848b5 |
| gfpo.md | 5.24 kB | | 1311651a |
| gkd_trainer.html | 119 kB | | 66692317 |
| gkd_trainer.md | 14.1 kB | | b56c6940 |
| gold_trainer.html | 156 kB | | 0b42839c |
| gold_trainer.md | 16.8 kB | | 8b617f99 |
| grpo_trainer.html | 554 kB | | 3c840504 |
| grpo_trainer.md | 53.8 kB | | 750a4d99 |
| grpo_with_replay_buffer.html | 89.6 kB | | e6943afb |
| grpo_with_replay_buffer.md | 6.16 kB | | ed0c5c56 |
| gspo_token.html | 50.2 kB | | 86f4704a |
| gspo_token.md | 4.27 kB | | 09388eaa |
| index.html | 28.8 kB | | b64cd7f5 |
| index.md | 3.68 kB | | 55bdb9e3 |
| installation.html | 13.9 kB | | f7dc86f2 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | d2280f13 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| judges.html | 122 kB | | f6612152 |
| judges.md | 15.8 kB | | f63c6e8c |
| kernels_hub.html | 26.8 kB | | bd4e3fb0 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 138 kB | | 32dc05b9 |
| kto_trainer.md | 19.4 kB | | b5c885d6 |
| liger_kernel_integration.html | 15 kB | | 84018b33 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 809 kB | | a0d332d7 |
| llms.txt | 4.91 kB | | fba55747 |
| lora_without_regret.html | 45 kB | | 1aa3a123 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 5dd110ad |
| merge_model_callback.md | 1.19 kB | | a0ddca2f |
| minillm.html | 183 kB | | 34a560cc |
| minillm.md | 16.5 kB | | c06e83b6 |
| minillm_trainer.html | 179 kB | | 7b8febee |
| minillm_trainer.md | 16.4 kB | | 93d23f00 |
| model_utils.html | 40.6 kB | | bd173b56 |
| model_utils.md | 3.42 kB | | 4a9048d4 |
| models.html | 128 kB | | 20e24be1 |
| models.md | 14.7 kB | | 9712e062 |
| nash_md_trainer.html | 130 kB | | 4cf504a0 |
| nash_md_trainer.md | 17.1 kB | | ef72ace1 |
| nemo_gym.html | 58.5 kB | | faeeecd4 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.37 kB | | 42792daf |
| online_dpo_trainer.html | 195 kB | | a36eef62 |
| online_dpo_trainer.md | 26.3 kB | | 3f85d131 |
| openenv.html | 88.2 kB | | 9321083e |
| openenv.md | 25.4 kB | | 94d2ec88 |
| orpo_trainer.html | 129 kB | | 01525a7f |
| orpo_trainer.md | 17.9 kB | | 839fe93d |
| others.html | 29.8 kB | | 3783109d |
| others.md | 2.29 kB | | 1e82c062 |
| paper_index.html | 717 kB | | eb76d3c3 |
| paper_index.md | 13.8 kB | | 7c80ab7a |
| papo_trainer.html | 111 kB | | 38721188 |
| papo_trainer.md | 8.82 kB | | c2f8d27a |
| peft_integration.html | 131 kB | | 3af4d121 |
| peft_integration.md | 23.9 kB | | 24449542 |
| ppo_trainer.html | 280 kB | | cc4948ba |
| ppo_trainer.md | 42 kB | | 754ffefa |
| prm_trainer.html | 117 kB | | a053df85 |
| prm_trainer.md | 13.9 kB | | 5d65c2d7 |
| ptt_integration.html | 29.3 kB | | c397a01a |
| ptt_integration.md | 4.27 kB | | 6a21357a |
|