| _app | | | 143 items |
| _toctree.yml | 3.29 kB | | 3ae9d845 |
| async_grpo_trainer.html | 108 kB | | f66b7ecb |
| async_grpo_trainer.md | 12.3 kB | | fa29d01b |
| bco_trainer.html | 130 kB | | c3d08778 |
| bco_trainer.md | 14.1 kB | | b8e01ae8 |
| bema_for_reference_model.html | 90 kB | | 5e643dee |
| bema_for_reference_model.md | 7.18 kB | | 022f20fa |
| callbacks.html | 95.8 kB | | c640b0dc |
| callbacks.md | 7.88 kB | | af84c164 |
| chat_template_utils.html | 45.5 kB | | f738e526 |
| chat_template_utils.md | 5.3 kB | | f1977a58 |
| clis.html | 53.4 kB | | cb823184 |
| clis.md | 12.8 kB | | 3b382942 |
| community_tutorials.html | 31 kB | | f3f74cd1 |
| community_tutorials.md | 11 kB | | ce8d81da |
| cpo_trainer.html | 144 kB | | 25641b0f |
| cpo_trainer.md | 23 kB | | f0c2587c |
| customization.html | 31 kB | | c29b2c6f |
| customization.md | 4.08 kB | | f193080b |
| data_utils.html | 62.9 kB | | 59110779 |
| data_utils.md | 6.32 kB | | 4cd3012a |
| dataset_formats.html | 223 kB | | e1bcd071 |
| dataset_formats.md | 40.2 kB | | 57ba3ae6 |
| deepspeed_integration.html | 15.8 kB | | 32e96b76 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | 0f957fc0 |
| distillation_trainer.md | 12.3 kB | | dd8a400a |
| distributing_training.html | 96.5 kB | | ab53deb9 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | ba4007f3 |
| dpo_trainer.md | 30.8 kB | | 31180bb5 |
| example_overview.html | 42.8 kB | | b707f940 |
| example_overview.md | 19.7 kB | | 4c8a4ded |
| experimental_overview.html | 10.8 kB | | 80871e8e |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | a593367a |
| gfpo.md | 5.24 kB | | dc8ce37b |
| gkd_trainer.html | 119 kB | | e52e2f46 |
| gkd_trainer.md | 14.1 kB | | 676ddb42 |
| gold_trainer.html | 166 kB | | 7eac1620 |
| gold_trainer.md | 18.1 kB | | 3b2b0966 |
| grpo_trainer.html | 559 kB | | 5cd80467 |
| grpo_trainer.md | 55.2 kB | | c2677a13 |
| grpo_with_replay_buffer.html | 89.6 kB | | d25e3ade |
| grpo_with_replay_buffer.md | 6.16 kB | | a079ed97 |
| gspo_token.html | 50.2 kB | | 7ae2b19b |
| gspo_token.md | 4.27 kB | | b7e4433c |
| index.html | 29 kB | | e25413c8 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 5d968a09 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | fe196bed |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | dd36058d |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 137 kB | | 5ce86a6e |
| kto_trainer.md | 18.1 kB | | 05ae1ac1 |
| liger_kernel_integration.html | 15 kB | | 2d7f8dc5 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 836 kB | | 94a0681a |
| llms.txt | 5 kB | | 9a6f9666 |
| lora_without_regret.html | 45 kB | | 2aa05bbc |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | ff6fd302 |
| merge_model_callback.md | 1.19 kB | | 47d10d7f |
| minillm_trainer.html | 179 kB | | 1a1c03b6 |
| minillm_trainer.md | 16.4 kB | | 94b4af42 |
| nash_md_trainer.html | 124 kB | | 3ae43a97 |
| nash_md_trainer.md | 16.3 kB | | cf877449 |
| nemo_gym.html | 58.5 kB | | f4cb4f4c |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.41 kB | | 239812ca |
| online_dpo_trainer.html | 179 kB | | b64d1d69 |
| online_dpo_trainer.md | 23.1 kB | | 27684c3f |
| openenv.html | 114 kB | | 922713f5 |
| openenv.md | 27.8 kB | | 60beb32b |
| orpo_trainer.html | 127 kB | | 7f8cb941 |
| orpo_trainer.md | 17.7 kB | | f1d1f90a |
| paper_index.html | 734 kB | | 2ec1cb0d |
| paper_index.md | 19.1 kB | | 7be3e129 |
| papo_trainer.html | 111 kB | | 62a64505 |
| papo_trainer.md | 8.82 kB | | cb6edd55 |
| peft_integration.html | 131 kB | | bf01cfb3 |
| peft_integration.md | 23.9 kB | | 8f00d0d3 |
| ppo_trainer.html | 278 kB | | 88ea19fd |
| ppo_trainer.md | 41.4 kB | | 98daa72f |
| prm_trainer.html | 117 kB | | af2f71c1 |
| prm_trainer.md | 13.9 kB | | 1457026e |
| ptt_integration.html | 29.3 kB | | f2e0b651 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | d1f08824 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | 7aaa670c |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | 66e00b69 |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
| reward_trainer.html | 175 kB | | a2134eb8 |
| reward_trainer.md | 21.5 kB | | 4f8eedf5 |
|