| _app | | | 150 items |
| _toctree.yml | 3.29 kB | | 3ae9d845 |
| async_grpo_trainer.html | 108 kB | | 166ec273 |
| async_grpo_trainer.md | 12.3 kB | | 273e4735 |
| bco_trainer.html | 130 kB | | 8f8c9d96 |
| bco_trainer.md | 14.1 kB | | 0e8ed62b |
| bema_for_reference_model.html | 90 kB | | 6a49b4b4 |
| bema_for_reference_model.md | 7.18 kB | | f16b3415 |
| callbacks.html | 95.8 kB | | a223a178 |
| callbacks.md | 7.88 kB | | 61037cb4 |
| chat_template_utils.html | 45.7 kB | | dd2b5996 |
| chat_template_utils.md | 5.34 kB | | 33c406f2 |
| clis.html | 53.4 kB | | b797b413 |
| clis.md | 12.8 kB | | df655283 |
| community_tutorials.html | 31 kB | | c5d4b225 |
| community_tutorials.md | 11 kB | | f05ce73b |
| cpo_trainer.html | 144 kB | | 00f5eef4 |
| cpo_trainer.md | 23 kB | | c44c5dfd |
| customization.html | 31 kB | | 97807acc |
| customization.md | 4.08 kB | | c0f0089c |
| data_utils.html | 62.9 kB | | f4a52f03 |
| data_utils.md | 6.32 kB | | a2983444 |
| dataset_formats.html | 223 kB | | 0a16452d |
| dataset_formats.md | 40.2 kB | | 7033850f |
| deepspeed_integration.html | 15.8 kB | | 83f7b745 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | 2282e2c6 |
| distillation_trainer.md | 12.3 kB | | 6624bfc1 |
| distributing_training.html | 96.5 kB | | efce0d4c |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | d0f18dcf |
| dpo_trainer.md | 30.8 kB | | eef6b964 |
| example_overview.html | 42.8 kB | | 2c63b92f |
| example_overview.md | 19.7 kB | | 97e4a2bb |
| experimental_overview.html | 10.8 kB | | 057adb16 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | b9501f7d |
| gfpo.md | 5.24 kB | | 0428e338 |
| gkd_trainer.html | 119 kB | | 1fe0e756 |
| gkd_trainer.md | 14.1 kB | | 81d8bf27 |
| gold_trainer.html | 166 kB | | 14655015 |
| gold_trainer.md | 18.1 kB | | 8a661786 |
| grpo_trainer.html | 560 kB | | b5c5ae39 |
| grpo_trainer.md | 55.4 kB | | fb7cded9 |
| grpo_with_replay_buffer.html | 89.6 kB | | d2676df3 |
| grpo_with_replay_buffer.md | 6.16 kB | | ea43a3e8 |
| gspo_token.html | 50.2 kB | | 28752101 |
| gspo_token.md | 4.27 kB | | 1c2371cc |
| index.html | 29 kB | | 366ba9bb |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | c6cb0b08 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | e1c0a83a |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | 2b470df7 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 137 kB | | 898170c4 |
| kto_trainer.md | 18.1 kB | | 33636426 |
| liger_kernel_integration.html | 15 kB | | da1baaff |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 836 kB | | 96c1c76b |
| llms.txt | 5 kB | | 664a8bf4 |
| lora_without_regret.html | 45 kB | | 143b27a3 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 82aee72c |
| merge_model_callback.md | 1.19 kB | | 1efaf515 |
| minillm_trainer.html | 179 kB | | 806552e1 |
| minillm_trainer.md | 16.4 kB | | 29ca6c4b |
| nash_md_trainer.html | 124 kB | | dfdf45c8 |
| nash_md_trainer.md | 16.3 kB | | de8900c9 |
| nemo_gym.html | 58.5 kB | | 8bd8b5a1 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.41 kB | | 71cfcde7 |
| online_dpo_trainer.html | 179 kB | | d34aaca7 |
| online_dpo_trainer.md | 23.1 kB | | 0918348d |
| openenv.html | 114 kB | | 4e464fee |
| openenv.md | 27.8 kB | | a1d1ca72 |
| orpo_trainer.html | 127 kB | | c56a6963 |
| orpo_trainer.md | 17.7 kB | | 520c03b6 |
| paper_index.html | 734 kB | | f7d14360 |
| paper_index.md | 19.1 kB | | bdd3a134 |
| papo_trainer.html | 111 kB | | 4011cdef |
| papo_trainer.md | 8.82 kB | | 3cf74ab3 |
| peft_integration.html | 131 kB | | 0a89adc5 |
| peft_integration.md | 23.9 kB | | fa090779 |
| ppo_trainer.html | 278 kB | | b8e89d56 |
| ppo_trainer.md | 41.4 kB | | f1d72658 |
| prm_trainer.html | 117 kB | | 6dec5359 |
| prm_trainer.md | 13.9 kB | | 91059b7d |
| ptt_integration.html | 29.3 kB | | 7393af4f |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 603cf61a |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | 2af2069b |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | f6ae58dd |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
| reward_trainer.html | 175 kB | | ef45ad97 |
| reward_trainer.md | 21.5 kB | | 29e70364 |
|