| _app | | | 173 items |
| _toctree.yml | 3.29 kB | | 3ae9d845 |
| async_grpo_trainer.html | 108 kB | | c62f24f9 |
| async_grpo_trainer.md | 12.3 kB | | 184ccbd9 |
| bco_trainer.html | 130 kB | | c5b6f9fa |
| bco_trainer.md | 14.1 kB | | 0f04a930 |
| bema_for_reference_model.html | 90 kB | | b7f37d2d |
| bema_for_reference_model.md | 7.18 kB | | 39a1ce0b |
| callbacks.html | 95.8 kB | | c0433b13 |
| callbacks.md | 7.88 kB | | b47230cc |
| chat_template_utils.html | 45.7 kB | | ca0cc309 |
| chat_template_utils.md | 5.34 kB | | d0361063 |
| clis.html | 53.4 kB | | bb1ea04f |
| clis.md | 12.8 kB | | eda01b53 |
| community_tutorials.html | 31 kB | | d8e32776 |
| community_tutorials.md | 11 kB | | d8c517df |
| cpo_trainer.html | 144 kB | | 4714025e |
| cpo_trainer.md | 23 kB | | 09a6fffd |
| customization.html | 31 kB | | dacd1a10 |
| customization.md | 4.08 kB | | da6d38c0 |
| data_utils.html | 62.9 kB | | a4a01cac |
| data_utils.md | 6.32 kB | | 924c2ce3 |
| dataset_formats.html | 223 kB | | 29d487e3 |
| dataset_formats.md | 40.2 kB | | 024e8faa |
| deepspeed_integration.html | 15.8 kB | | f2f7f20f |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | c4ec96c1 |
| distillation_trainer.md | 12.3 kB | | cce6b2c2 |
| distributing_training.html | 96.5 kB | | 3a948070 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | f2b1ae21 |
| dpo_trainer.md | 30.8 kB | | a5166fd8 |
| example_overview.html | 42.8 kB | | 982c22f0 |
| example_overview.md | 19.7 kB | | 64a24a42 |
| experimental_overview.html | 10.8 kB | | 89278312 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | f6d533fc |
| gfpo.md | 5.24 kB | | eb982ccc |
| gkd_trainer.html | 119 kB | | 1c739c11 |
| gkd_trainer.md | 14.1 kB | | 370d5722 |
| gold_trainer.html | 166 kB | | 4bdd5e58 |
| gold_trainer.md | 18.1 kB | | 83e24b63 |
| grpo_trainer.html | 560 kB | | 605e4dc3 |
| grpo_trainer.md | 55.4 kB | | 8af28c14 |
| grpo_with_replay_buffer.html | 89.6 kB | | 1c960b53 |
| grpo_with_replay_buffer.md | 6.16 kB | | 7e598f15 |
| gspo_token.html | 50.2 kB | | b7eaf60f |
| gspo_token.md | 4.27 kB | | 7cda20a3 |
| index.html | 29 kB | | 7fc572b7 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | ee5880f4 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | fa2963c7 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | 129ab8d7 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 137 kB | | bcdee214 |
| kto_trainer.md | 18.1 kB | | 524a8173 |
| liger_kernel_integration.html | 15 kB | | c583ffe3 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 836 kB | | 56ee4b09 |
| llms.txt | 5 kB | | 272a9cd3 |
| lora_without_regret.html | 45 kB | | bb1a7fac |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | ae9e351b |
| merge_model_callback.md | 1.19 kB | | bc5b9a41 |
| minillm_trainer.html | 179 kB | | f0a18fab |
| minillm_trainer.md | 16.4 kB | | 3543ecc2 |
| nash_md_trainer.html | 124 kB | | 8e065714 |
| nash_md_trainer.md | 16.3 kB | | f6de3e8f |
| nemo_gym.html | 58.5 kB | | e1a6076c |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.41 kB | | 2863856f |
| online_dpo_trainer.html | 179 kB | | b74d333b |
| online_dpo_trainer.md | 23.1 kB | | 3ce3f2c7 |
| openenv.html | 114 kB | | 791e15d1 |
| openenv.md | 27.8 kB | | 1adca23b |
| orpo_trainer.html | 127 kB | | 53bc4b5c |
| orpo_trainer.md | 17.7 kB | | 9b48036b |
| paper_index.html | 734 kB | | 64c5234c |
| paper_index.md | 19.1 kB | | a52af4b6 |
| papo_trainer.html | 111 kB | | b6145603 |
| papo_trainer.md | 8.82 kB | | b51404d1 |
| peft_integration.html | 131 kB | | 66e0fbb5 |
| peft_integration.md | 23.9 kB | | 2dddcc0f |
| ppo_trainer.html | 278 kB | | d90bcf63 |
| ppo_trainer.md | 41.4 kB | | c557d83b |
| prm_trainer.html | 117 kB | | e85ec41b |
| prm_trainer.md | 13.9 kB | | c11299f9 |
| ptt_integration.html | 29.3 kB | | fe301d74 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 321857c5 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | 3df57303 |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | a4d91cfe |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
| reward_trainer.html | 175 kB | | 29adbef9 |
| reward_trainer.md | 21.5 kB | | 30da5681 |
|