| _app | | | 135 items |
| _toctree.yml | 3.29 kB | | 3ae9d845 |
| async_grpo_trainer.html | 108 kB | | fc50cadf |
| async_grpo_trainer.md | 12.3 kB | | ca583f1a |
| bco_trainer.html | 130 kB | | f75d44ba |
| bco_trainer.md | 14.1 kB | | 371d7d0d |
| bema_for_reference_model.html | 90 kB | | 5fef3940 |
| bema_for_reference_model.md | 7.18 kB | | a548c793 |
| callbacks.html | 95.8 kB | | dac21a49 |
| callbacks.md | 7.88 kB | | 3cbb491c |
| chat_template_utils.html | 45.5 kB | | 804c5566 |
| chat_template_utils.md | 5.3 kB | | 3db9eec5 |
| clis.html | 53.4 kB | | d6d54566 |
| clis.md | 12.8 kB | | b8b6433b |
| community_tutorials.html | 31 kB | | d0e60f7c |
| community_tutorials.md | 11 kB | | 34eb7db6 |
| cpo_trainer.html | 144 kB | | 743357ac |
| cpo_trainer.md | 23 kB | | 9556536b |
| customization.html | 31 kB | | eae092d1 |
| customization.md | 4.08 kB | | 3082be26 |
| data_utils.html | 62.9 kB | | c5aef936 |
| data_utils.md | 6.32 kB | | 80e08fed |
| dataset_formats.html | 223 kB | | 59cd8f8c |
| dataset_formats.md | 40.2 kB | | dd15cb6a |
| deepspeed_integration.html | 15.8 kB | | a5656032 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | f2ca2dc8 |
| distillation_trainer.md | 12.3 kB | | e12a15b7 |
| distributing_training.html | 96.5 kB | | deaf91a9 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | e350b1b3 |
| dpo_trainer.md | 30.8 kB | | a42b8e2e |
| example_overview.html | 42.7 kB | | 1b6bd052 |
| example_overview.md | 19.7 kB | | 8addb6b4 |
| experimental_overview.html | 10.8 kB | | f3627123 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | b654b6a1 |
| gfpo.md | 5.24 kB | | f83d3e96 |
| gkd_trainer.html | 119 kB | | a07ec660 |
| gkd_trainer.md | 14.1 kB | | 446fe558 |
| gold_trainer.html | 166 kB | | 56953011 |
| gold_trainer.md | 18.1 kB | | fe13ce6a |
| grpo_trainer.html | 560 kB | | 611c3429 |
| grpo_trainer.md | 55.4 kB | | 9bd3cfa7 |
| grpo_with_replay_buffer.html | 89.6 kB | | 4f57a6fd |
| grpo_with_replay_buffer.md | 6.16 kB | | 595503a6 |
| gspo_token.html | 50.2 kB | | 62a6469e |
| gspo_token.md | 4.27 kB | | 7794c18b |
| index.html | 29 kB | | f16cc771 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | ac4d8907 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 255a4613 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | 972c7502 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 137 kB | | ed3ea4ee |
| kto_trainer.md | 18.1 kB | | 1eb211e6 |
| liger_kernel_integration.html | 15 kB | | 9cfa06c1 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 836 kB | | bfdb3f84 |
| llms.txt | 5 kB | | 60b16981 |
| lora_without_regret.html | 45 kB | | cf350f8a |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 9069a62b |
| merge_model_callback.md | 1.19 kB | | 7065aab3 |
| minillm_trainer.html | 179 kB | | e3748fb5 |
| minillm_trainer.md | 16.4 kB | | d5bb2c02 |
| nash_md_trainer.html | 124 kB | | 05e2abe5 |
| nash_md_trainer.md | 16.3 kB | | 5197f85e |
| nemo_gym.html | 58.5 kB | | a22c26ca |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.41 kB | | 36f096e4 |
| online_dpo_trainer.html | 179 kB | | 70ac6443 |
| online_dpo_trainer.md | 23.1 kB | | 44252671 |
| openenv.html | 114 kB | | 177aac75 |
| openenv.md | 27.8 kB | | 19c9e5e5 |
| orpo_trainer.html | 127 kB | | 6a816ff6 |
| orpo_trainer.md | 17.7 kB | | 283e4c2f |
| paper_index.html | 734 kB | | 7b9f8938 |
| paper_index.md | 19.1 kB | | 9c08d3d8 |
| papo_trainer.html | 111 kB | | ca7321f6 |
| papo_trainer.md | 8.82 kB | | 8bb81a16 |
| peft_integration.html | 131 kB | | 70890970 |
| peft_integration.md | 23.9 kB | | b5b45258 |
| ppo_trainer.html | 278 kB | | d7eab232 |
| ppo_trainer.md | 41.4 kB | | 76a4b361 |
| prm_trainer.html | 117 kB | | dbb93c33 |
| prm_trainer.md | 13.9 kB | | d8c5398b |
| ptt_integration.html | 29.3 kB | | b065e10a |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 7822bc4f |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | 17d1d6ea |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | a12196a7 |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
| reward_trainer.html | 175 kB | | 76500ed1 |
| reward_trainer.md | 21.5 kB | | 42eafe37 |
|