| _app | | | 346 items |
| _toctree.yml | 3.38 kB | | 9da8f3eb |
| async_grpo_trainer.html | 108 kB | | 00a08060 |
| async_grpo_trainer.md | 12.3 kB | | a8dbbc22 |
| bco_trainer.html | 130 kB | | ab10da53 |
| bco_trainer.md | 14.1 kB | | 961995ce |
| bema_for_reference_model.html | 90 kB | | c39818da |
| bema_for_reference_model.md | 7.18 kB | | 1c8387de |
| callbacks.html | 95.8 kB | | 2f6aad9e |
| callbacks.md | 7.88 kB | | ebd8ddf1 |
| chat_template_utils.html | 46.2 kB | | b7e3d682 |
| chat_template_utils.md | 5.77 kB | | b72554bd |
| chat_templates.html | 35.4 kB | | 0dd3bac2 |
| chat_templates.md | 6.48 kB | | 9b8b1bd5 |
| clis.html | 53.4 kB | | 47124092 |
| clis.md | 12.8 kB | | d2ff4bc7 |
| community_tutorials.html | 31 kB | | 7a0c7e72 |
| community_tutorials.md | 11 kB | | 132ac7a6 |
| cpo_trainer.html | 144 kB | | f7a268cc |
| cpo_trainer.md | 23 kB | | 238ca635 |
| customization.html | 31 kB | | a2b96bd6 |
| customization.md | 4.08 kB | | a0ad9973 |
| data_utils.html | 62.7 kB | | 3e235003 |
| data_utils.md | 6.87 kB | | cebc8d06 |
| dataset_formats.html | 223 kB | | e99b8e9a |
| dataset_formats.md | 40.2 kB | | 7b41658d |
| deepspeed_integration.html | 15.8 kB | | ec293c38 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 161 kB | | e70dbd51 |
| distillation_trainer.md | 12.3 kB | | 8378c1f7 |
| distributing_training.html | 96.5 kB | | 51fa75a2 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 233 kB | | 7c438ef3 |
| dpo_trainer.md | 30.8 kB | | 5973ba9e |
| example_overview.html | 42.7 kB | | ba1d51ef |
| example_overview.md | 19.7 kB | | ce8fdac9 |
| experimental_overview.html | 10.8 kB | | aff93bec |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 85 kB | | 8015580e |
| gfpo.md | 5.24 kB | | 54473490 |
| gkd_trainer.html | 119 kB | | 24379b48 |
| gkd_trainer.md | 14.1 kB | | cb509b42 |
| gold_trainer.html | 166 kB | | 22722464 |
| gold_trainer.md | 18.1 kB | | 4f729797 |
| grpo_trainer.html | 561 kB | | 2783ddbc |
| grpo_trainer.md | 55.9 kB | | ad47faba |
| grpo_with_replay_buffer.html | 90.3 kB | | 8983dc8f |
| grpo_with_replay_buffer.md | 6.16 kB | | 4304ff4d |
| gspo_token.html | 50.2 kB | | cfa42378 |
| gspo_token.md | 4.27 kB | | 5f6346f1 |
| index.html | 29 kB | | 8a3d1743 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | f0846bf6 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 8af7678e |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | 37a4a379 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 134 kB | | 176f7243 |
| kto_trainer.md | 18 kB | | 66591793 |
| liger_kernel_integration.html | 15 kB | | 69cb66e8 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 870 kB | | 02e81ab0 |
| llms.txt | 5.15 kB | | 95e37277 |
| lora_without_regret.html | 45 kB | | 3a91aa78 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | ff1137f3 |
| merge_model_callback.md | 1.19 kB | | e782b58d |
| minillm_trainer.html | 180 kB | | bfe9dbfc |
| minillm_trainer.md | 16.4 kB | | 0c5da200 |
| nash_md_trainer.html | 125 kB | | 7dbe33a6 |
| nash_md_trainer.md | 16.3 kB | | c7110af4 |
| nemo_gym.html | 58.5 kB | | ed87cc7c |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.45 kB | | ea619058 |
| online_dpo_trainer.html | 180 kB | | 96159f34 |
| online_dpo_trainer.md | 23.1 kB | | 62717421 |
| openenv.html | 114 kB | | fe51768b |
| openenv.md | 27.8 kB | | 95a5f757 |
| orpo_trainer.html | 127 kB | | 73d48d2e |
| orpo_trainer.md | 17.7 kB | | 4741ac16 |
| paper_index.html | 742 kB | | eb5a2971 |
| paper_index.md | 19.1 kB | | be5243ec |
| papo_trainer.html | 112 kB | | 78b9ce0a |
| papo_trainer.md | 8.82 kB | | 3868c919 |
| peft_integration.html | 131 kB | | 354e93f4 |
| peft_integration.md | 23.9 kB | | 18bc72e2 |
| ppo_trainer.html | 279 kB | | 5ad6d3a1 |
| ppo_trainer.md | 41.4 kB | | b3a43683 |
| prm_trainer.html | 118 kB | | f76077eb |
| prm_trainer.md | 13.9 kB | | 9e746125 |
| ptt_integration.html | 29.3 kB | | 1d2fe4ac |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 2fcee5a2 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 95.4 kB | | d7c70726 |
| rapidfire_integration.md | 17.7 kB | | 08fed5af |
| reducing_memory_usage.html | 57.1 kB | | d398dab8 |
| reducing_memory_usage.md | 13.7 kB | | a0de493e |
|