| _app | | | 139 items |
| _toctree.yml | 3.22 kB | | ca36b740 |
| async_grpo_trainer.html | 108 kB | | 242168dc |
| async_grpo_trainer.md | 12.3 kB | | 84d97593 |
| bco_trainer.html | 131 kB | | c3e33615 |
| bco_trainer.md | 14.4 kB | | 2cd169ac |
| bema_for_reference_model.html | 90 kB | | 8cb47cda |
| bema_for_reference_model.md | 7.18 kB | | 4546974c |
| callbacks.html | 95.8 kB | | 407663a3 |
| callbacks.md | 7.88 kB | | d78e1dce |
| chat_template_utils.html | 43.9 kB | | 68b877f1 |
| chat_template_utils.md | 4.65 kB | | f96b6647 |
| clis.html | 53.4 kB | | efee5dcf |
| clis.md | 12.8 kB | | 63831c52 |
| community_tutorials.html | 31 kB | | 094379fe |
| community_tutorials.md | 11 kB | | a6442460 |
| cpo_trainer.html | 146 kB | | a2bf8edc |
| cpo_trainer.md | 23.2 kB | | 0c6070f9 |
| customization.html | 31 kB | | 3e80f8f5 |
| customization.md | 4.08 kB | | 19e2bcca |
| data_utils.html | 62.9 kB | | 76e0beff |
| data_utils.md | 6.32 kB | | 6f8bd185 |
| dataset_formats.html | 223 kB | | b615c3a5 |
| dataset_formats.md | 40.2 kB | | af40a349 |
| deepspeed_integration.html | 15.8 kB | | 235efb1b |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distributing_training.html | 96.5 kB | | 63c73385 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 231 kB | | a0621429 |
| dpo_trainer.md | 30.6 kB | | 04e7c4de |
| example_overview.html | 39.6 kB | | c9709be1 |
| example_overview.md | 19.5 kB | | e57562b2 |
| experimental_overview.html | 10.8 kB | | adb55a4f |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | e9e95a76 |
| gfpo.md | 5.24 kB | | 735fd26f |
| gkd_trainer.html | 119 kB | | 57cde06b |
| gkd_trainer.md | 14.1 kB | | fcbf3e80 |
| gold_trainer.html | 156 kB | | e1c7e355 |
| gold_trainer.md | 16.8 kB | | dfc69043 |
| grpo_trainer.html | 554 kB | | 9dfda7b8 |
| grpo_trainer.md | 53.8 kB | | df0880a3 |
| grpo_with_replay_buffer.html | 89.6 kB | | a7d15e7e |
| grpo_with_replay_buffer.md | 6.16 kB | | 48cd198c |
| gspo_token.html | 50.2 kB | | 44fbc846 |
| gspo_token.md | 4.27 kB | | e231f35c |
| index.html | 28.8 kB | | a752a6cf |
| index.md | 3.68 kB | | 55bdb9e3 |
| installation.html | 13.9 kB | | 45877312 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 670f2143 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| judges.html | 122 kB | | d551388e |
| judges.md | 15.8 kB | | 25fa34ab |
| kernels_hub.html | 26.8 kB | | 7ba658ec |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 138 kB | | cda88a15 |
| kto_trainer.md | 19.4 kB | | 52b96e48 |
| liger_kernel_integration.html | 15 kB | | 4006eb8f |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 809 kB | | 19687d3c |
| llms.txt | 4.91 kB | | 0e006103 |
| lora_without_regret.html | 45 kB | | 73ce8b4c |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 47a15aee |
| merge_model_callback.md | 1.19 kB | | 19ae3eca |
| minillm_trainer.html | 179 kB | | cec74a69 |
| minillm_trainer.md | 16.4 kB | | 21d72316 |
| nash_md_trainer.html | 130 kB | | 8fccd269 |
| nash_md_trainer.md | 17.1 kB | | 0795f4ee |
| nemo_gym.html | 58.5 kB | | b8fba3c3 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.37 kB | | 0bfadbef |
| online_dpo_trainer.html | 195 kB | | 0a909d35 |
| online_dpo_trainer.md | 26.3 kB | | a47533b9 |
| openenv.html | 88.2 kB | | 212b21d5 |
| openenv.md | 25.4 kB | | 752797a9 |
| orpo_trainer.html | 129 kB | | 8b5c8d7c |
| orpo_trainer.md | 17.9 kB | | 9eddafb8 |
| paper_index.html | 717 kB | | bbe37587 |
| paper_index.md | 13.8 kB | | 7945c371 |
| papo_trainer.html | 111 kB | | 6f3075e2 |
| papo_trainer.md | 8.82 kB | | 0e1b0bd7 |
| peft_integration.html | 131 kB | | 5484bf6f |
| peft_integration.md | 23.9 kB | | a4bbfb0b |
| ppo_trainer.html | 280 kB | | efa78c7f |
| ppo_trainer.md | 42 kB | | e759961d |
| prm_trainer.html | 117 kB | | c0267732 |
| prm_trainer.md | 13.9 kB | | df79ac1e |
| ptt_integration.html | 29.3 kB | | 2ee8cc8d |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 7f679812 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | 9cd01227 |
| rapidfire_integration.md | 12.8 kB | | c14e6d99 |
| reducing_memory_usage.html | 52.4 kB | | b9e17d2b |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
| reward_trainer.html | 175 kB | | 91357db8 |
| reward_trainer.md | 21.5 kB | | cd97dfe7 |
|