| _app | | | 259 items |
| _toctree.yml | 3.29 kB | | 3ae9d845 |
| async_grpo_trainer.html | 108 kB | | c1a38a21 |
| async_grpo_trainer.md | 12.3 kB | | bf59a0ed |
| bco_trainer.html | 130 kB | | 0be6d6ef |
| bco_trainer.md | 14.1 kB | | 7635661b |
| bema_for_reference_model.html | 90 kB | | 6288c053 |
| bema_for_reference_model.md | 7.18 kB | | 87b70b42 |
| callbacks.html | 95.8 kB | | a62b208f |
| callbacks.md | 7.88 kB | | cf385811 |
| chat_template_utils.html | 45.5 kB | | f3168c28 |
| chat_template_utils.md | 5.3 kB | | 30bdbb91 |
| clis.html | 53.4 kB | | 04a207f7 |
| clis.md | 12.8 kB | | 2316be8c |
| community_tutorials.html | 31 kB | | 20760206 |
| community_tutorials.md | 11 kB | | f9015cbc |
| cpo_trainer.html | 144 kB | | b592766b |
| cpo_trainer.md | 23 kB | | 9143567b |
| customization.html | 31 kB | | 90821ed6 |
| customization.md | 4.08 kB | | 74d003e9 |
| data_utils.html | 62.9 kB | | 01c5eadb |
| data_utils.md | 6.32 kB | | 2eb0670f |
| dataset_formats.html | 223 kB | | 3c591ea8 |
| dataset_formats.md | 40.2 kB | | 6f441d95 |
| deepspeed_integration.html | 15.8 kB | | 86eb608c |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | 859e7417 |
| distillation_trainer.md | 12.3 kB | | 8193f948 |
| distributing_training.html | 96.5 kB | | 8147bb13 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | e34f21f6 |
| dpo_trainer.md | 30.8 kB | | 2084f24e |
| example_overview.html | 42.7 kB | | 90d5b6ab |
| example_overview.md | 19.7 kB | | 6eefb06f |
| experimental_overview.html | 10.8 kB | | de8f3ac0 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | 8ece9db1 |
| gfpo.md | 5.24 kB | | b5827839 |
| gkd_trainer.html | 119 kB | | 57310ab5 |
| gkd_trainer.md | 14.1 kB | | caff8872 |
| gold_trainer.html | 166 kB | | 58583d4a |
| gold_trainer.md | 18.1 kB | | 001eb73a |
| grpo_trainer.html | 559 kB | | 53befcc0 |
| grpo_trainer.md | 55.2 kB | | b610de23 |
| grpo_with_replay_buffer.html | 89.6 kB | | c5764997 |
| grpo_with_replay_buffer.md | 6.16 kB | | 7ed9cf00 |
| gspo_token.html | 50.2 kB | | 0378fa14 |
| gspo_token.md | 4.27 kB | | f152382b |
| index.html | 29 kB | | cff277da |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 6820ab2d |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 1ef682c6 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| judges.html | 122 kB | | dde594ad |
| judges.md | 15.8 kB | | 5776256f |
| kernels_hub.html | 26.8 kB | | dd94f9c3 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 137 kB | | 1d446b41 |
| kto_trainer.md | 18.1 kB | | 946f8f7b |
| liger_kernel_integration.html | 15 kB | | 0b3831d9 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 836 kB | | b9ddb05b |
| llms.txt | 5 kB | | af16aa6f |
| lora_without_regret.html | 45 kB | | 3bbb15de |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 99604c62 |
| merge_model_callback.md | 1.19 kB | | beff4143 |
| minillm_trainer.html | 179 kB | | 68200747 |
| minillm_trainer.md | 16.4 kB | | 7cc09282 |
| nash_md_trainer.html | 124 kB | | e9234c4e |
| nash_md_trainer.md | 16.3 kB | | cae93a55 |
| nemo_gym.html | 58.5 kB | | bd7dda26 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.41 kB | | 8ef392fc |
| online_dpo_trainer.html | 179 kB | | 3d355d49 |
| online_dpo_trainer.md | 23.1 kB | | 277b3255 |
| openenv.html | 114 kB | | 198f3b5c |
| openenv.md | 27.8 kB | | a6cca64a |
| orpo_trainer.html | 127 kB | | d292a603 |
| orpo_trainer.md | 17.7 kB | | 20713dd1 |
| paper_index.html | 734 kB | | 9951db8a |
| paper_index.md | 19.1 kB | | a111665d |
| papo_trainer.html | 111 kB | | e3e2a590 |
| papo_trainer.md | 8.82 kB | | d533ab89 |
| peft_integration.html | 131 kB | | b2e48f49 |
| peft_integration.md | 23.9 kB | | 9dee33f8 |
| ppo_trainer.html | 278 kB | | 9b3741bc |
| ppo_trainer.md | 41.4 kB | | 4c0d150b |
| prm_trainer.html | 117 kB | | e54cf542 |
| prm_trainer.md | 13.9 kB | | 23cd9110 |
| ptt_integration.html | 29.3 kB | | a94c54fc |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | da599ca7 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | 6598e2d3 |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | 49c2733e |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
|