| _app | | | 141 items |
| _toctree.yml | 3.29 kB | | 3ae9d845 |
| async_grpo_trainer.html | 108 kB | | 60adb7aa |
| async_grpo_trainer.md | 12.3 kB | | 4e36edb3 |
| bco_trainer.html | 130 kB | | fc9cbe54 |
| bco_trainer.md | 14.1 kB | | da1b96e3 |
| bema_for_reference_model.html | 90 kB | | 6260f105 |
| bema_for_reference_model.md | 7.18 kB | | e8634f94 |
| callbacks.html | 95.8 kB | | 78ae78ec |
| callbacks.md | 7.88 kB | | 8266c6c4 |
| chat_template_utils.html | 45.7 kB | | e2044dd6 |
| chat_template_utils.md | 5.34 kB | | 6ab2ec9f |
| clis.html | 53.4 kB | | 4027a970 |
| clis.md | 12.8 kB | | 5cf11b99 |
| community_tutorials.html | 31 kB | | 510f7a35 |
| community_tutorials.md | 11 kB | | 5c6f9742 |
| cpo_trainer.html | 144 kB | | 7a6a4184 |
| cpo_trainer.md | 23 kB | | 96a7cfb4 |
| customization.html | 31 kB | | 98fbb662 |
| customization.md | 4.08 kB | | fd21be8a |
| data_utils.html | 62.9 kB | | 986f53ec |
| data_utils.md | 6.32 kB | | f27b2b9b |
| dataset_formats.html | 223 kB | | 56a9c96e |
| dataset_formats.md | 40.2 kB | | 7229dc48 |
| deepspeed_integration.html | 15.8 kB | | 22001137 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | 8d23f5fc |
| distillation_trainer.md | 12.3 kB | | fe196a2c |
| distributing_training.html | 96.5 kB | | 29b10b48 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | 6c1a172e |
| dpo_trainer.md | 30.8 kB | | a97f51de |
| example_overview.html | 42.7 kB | | c863f2d3 |
| example_overview.md | 19.7 kB | | 122da2f7 |
| experimental_overview.html | 10.8 kB | | d0cc53cb |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | 288be627 |
| gfpo.md | 5.24 kB | | ffa37a55 |
| gkd_trainer.html | 119 kB | | 681ccbb9 |
| gkd_trainer.md | 14.1 kB | | 8e10f280 |
| gold_trainer.html | 166 kB | | ce7f26c8 |
| gold_trainer.md | 18.1 kB | | 3ef4f9b1 |
| grpo_trainer.html | 560 kB | | b1c62f69 |
| grpo_trainer.md | 55.4 kB | | 63201cf6 |
| grpo_with_replay_buffer.html | 89.6 kB | | 7f38f244 |
| grpo_with_replay_buffer.md | 6.16 kB | | dfe44016 |
| gspo_token.html | 50.2 kB | | 7f6311ac |
| gspo_token.md | 4.27 kB | | bf40d8da |
| index.html | 29 kB | | 5ec72dcf |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 25625a70 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | cd828082 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | cabb8bbf |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 137 kB | | 47a68e99 |
| kto_trainer.md | 18.1 kB | | fc8ebcd7 |
| liger_kernel_integration.html | 15 kB | | dc478a09 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 836 kB | | dbcf375c |
| llms.txt | 5 kB | | 7b9cbb21 |
| lora_without_regret.html | 45 kB | | d1399779 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 6df00772 |
| merge_model_callback.md | 1.19 kB | | f86da0ec |
| minillm_trainer.html | 179 kB | | 64a8a4f6 |
| minillm_trainer.md | 16.4 kB | | dd1c99b9 |
| nash_md_trainer.html | 124 kB | | 72b301f6 |
| nash_md_trainer.md | 16.3 kB | | 9d44ed06 |
| nemo_gym.html | 58.5 kB | | ff2be2c0 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.41 kB | | 698b325e |
| online_dpo_trainer.html | 179 kB | | a07b0549 |
| online_dpo_trainer.md | 23.1 kB | | e2f84a55 |
| openenv.html | 114 kB | | 6650691a |
| openenv.md | 27.8 kB | | d2bf1158 |
| orpo_trainer.html | 127 kB | | f995ec06 |
| orpo_trainer.md | 17.7 kB | | b659c5ed |
| paper_index.html | 734 kB | | 112ea1bf |
| paper_index.md | 19.1 kB | | 45fba852 |
| papo_trainer.html | 111 kB | | 433ddce2 |
| papo_trainer.md | 8.82 kB | | 1362c202 |
| peft_integration.html | 131 kB | | 1c29f875 |
| peft_integration.md | 23.9 kB | | 970ddd08 |
| ppo_trainer.html | 278 kB | | 5240a7f2 |
| ppo_trainer.md | 41.4 kB | | 9292be70 |
| prm_trainer.html | 117 kB | | cd0e3261 |
| prm_trainer.md | 13.9 kB | | 35147fd1 |
| ptt_integration.html | 29.3 kB | | 7c4c7877 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 75d7eddb |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | cbd41cb4 |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | 87ec9c04 |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
| reward_trainer.html | 175 kB | | cfc1c19d |
| reward_trainer.md | 21.5 kB | | 232a376d |
|