| _app | | | 135 items |
| _toctree.yml | 3.29 kB | | 3ae9d845 |
| async_grpo_trainer.html | 108 kB | | eda7eb8a |
| async_grpo_trainer.md | 12.3 kB | | 22f3d85e |
| bco_trainer.html | 130 kB | | 3c6e8a72 |
| bco_trainer.md | 14.1 kB | | 9b870a61 |
| bema_for_reference_model.html | 90 kB | | ddb2b171 |
| bema_for_reference_model.md | 7.18 kB | | c5ed9a83 |
| callbacks.html | 95.8 kB | | e86d6122 |
| callbacks.md | 7.88 kB | | 24e0af6e |
| chat_template_utils.html | 45.5 kB | | 309ad7bf |
| chat_template_utils.md | 5.3 kB | | 1449199e |
| clis.html | 53.4 kB | | aa3c6720 |
| clis.md | 12.8 kB | | 7571db72 |
| community_tutorials.html | 31 kB | | 3e1dbeb0 |
| community_tutorials.md | 11 kB | | f95ff300 |
| cpo_trainer.html | 144 kB | | 33b877ce |
| cpo_trainer.md | 23 kB | | a63f7ae7 |
| customization.html | 31 kB | | eaaba804 |
| customization.md | 4.08 kB | | 6f687016 |
| data_utils.html | 62.9 kB | | 771f9971 |
| data_utils.md | 6.32 kB | | f220fe74 |
| dataset_formats.html | 223 kB | | 334069b5 |
| dataset_formats.md | 40.2 kB | | 850be89a |
| deepspeed_integration.html | 15.8 kB | | 9be16032 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | 87f968e4 |
| distillation_trainer.md | 12.3 kB | | 910d2331 |
| distributing_training.html | 96.5 kB | | c7b77165 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | 991bad16 |
| dpo_trainer.md | 30.8 kB | | f1fb07d5 |
| example_overview.html | 42.7 kB | | c251bc6f |
| example_overview.md | 19.7 kB | | 9ad2237a |
| experimental_overview.html | 10.8 kB | | 8db34d15 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | fd164434 |
| gfpo.md | 5.24 kB | | 8ebedebb |
| gkd_trainer.html | 119 kB | | cba5ab01 |
| gkd_trainer.md | 14.1 kB | | c836ea4e |
| gold_trainer.html | 166 kB | | 6cb43bf0 |
| gold_trainer.md | 18.1 kB | | 5daa5bcb |
| grpo_trainer.html | 560 kB | | 1b1dcef7 |
| grpo_trainer.md | 55.4 kB | | 00520704 |
| grpo_with_replay_buffer.html | 89.6 kB | | b6a9bd09 |
| grpo_with_replay_buffer.md | 6.16 kB | | a70628de |
| gspo_token.html | 50.2 kB | | 717cf925 |
| gspo_token.md | 4.27 kB | | b14a4a15 |
| index.html | 29 kB | | 6439ffe1 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 3c3903b0 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 9bd5df0e |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | 46a5a8d3 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 137 kB | | 996d1fc7 |
| kto_trainer.md | 18.1 kB | | 3f899b49 |
| liger_kernel_integration.html | 15 kB | | df1e121c |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 836 kB | | 06fc58a0 |
| llms.txt | 5 kB | | 3103689f |
| lora_without_regret.html | 45 kB | | ecd04160 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | e74ff38e |
| merge_model_callback.md | 1.19 kB | | 91be2a8c |
| minillm_trainer.html | 179 kB | | 3c5c214d |
| minillm_trainer.md | 16.4 kB | | aae65cb6 |
| nash_md_trainer.html | 124 kB | | 522e59d3 |
| nash_md_trainer.md | 16.3 kB | | e141e3f5 |
| nemo_gym.html | 58.5 kB | | f06ca564 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.41 kB | | e42494fb |
| online_dpo_trainer.html | 179 kB | | 9c349328 |
| online_dpo_trainer.md | 23.1 kB | | 5710b6c6 |
| openenv.html | 114 kB | | 831a1e74 |
| openenv.md | 27.8 kB | | cfa3218d |
| orpo_trainer.html | 127 kB | | 3fc15b1a |
| orpo_trainer.md | 17.7 kB | | c068fe85 |
| paper_index.html | 734 kB | | 75790c3b |
| paper_index.md | 19.1 kB | | 5e723e29 |
| papo_trainer.html | 111 kB | | bcb06e38 |
| papo_trainer.md | 8.82 kB | | 01ae949b |
| peft_integration.html | 131 kB | | 1a218f9e |
| peft_integration.md | 23.9 kB | | cbf194ee |
| ppo_trainer.html | 278 kB | | e0c61cfe |
| ppo_trainer.md | 41.4 kB | | 15935c6b |
| prm_trainer.html | 117 kB | | 36e39382 |
| prm_trainer.md | 13.9 kB | | 96cdfe86 |
| ptt_integration.html | 29.3 kB | | 2f82b6c5 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | a28331e7 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | b618fd95 |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | e092376a |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
| reward_trainer.html | 175 kB | | 2e99c5ca |
| reward_trainer.md | 21.5 kB | | 7540e348 |
|