| _app | | | 135 items |
| _toctree.yml | 3.29 kB | | 3ae9d845 |
| async_grpo_trainer.html | 108 kB | | 24c90d50 |
| async_grpo_trainer.md | 12.3 kB | | 89d00ae8 |
| bco_trainer.html | 130 kB | | 301ff560 |
| bco_trainer.md | 14.1 kB | | aa2204f3 |
| bema_for_reference_model.html | 90 kB | | a14975e7 |
| bema_for_reference_model.md | 7.18 kB | | 98b9197b |
| callbacks.html | 95.8 kB | | 009bb5df |
| callbacks.md | 7.88 kB | | 35f6d50c |
| chat_template_utils.html | 45.5 kB | | 61306cf8 |
| chat_template_utils.md | 5.3 kB | | 1ff545c2 |
| clis.html | 53.4 kB | | b0e162a2 |
| clis.md | 12.8 kB | | c4ac7b49 |
| community_tutorials.html | 31 kB | | 7771a1f0 |
| community_tutorials.md | 11 kB | | 358eac15 |
| cpo_trainer.html | 144 kB | | 5eff6b3e |
| cpo_trainer.md | 23 kB | | 32257b70 |
| customization.html | 31 kB | | 83245710 |
| customization.md | 4.08 kB | | 49a8ad99 |
| data_utils.html | 62.9 kB | | 38387b2f |
| data_utils.md | 6.32 kB | | 808d0e40 |
| dataset_formats.html | 223 kB | | eed462d9 |
| dataset_formats.md | 40.2 kB | | cedcfa31 |
| deepspeed_integration.html | 15.8 kB | | 7bde680f |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | b43d819d |
| distillation_trainer.md | 12.3 kB | | 90aac52b |
| distributing_training.html | 96.5 kB | | b04b66af |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | 819300d2 |
| dpo_trainer.md | 30.8 kB | | e9148e83 |
| example_overview.html | 42.8 kB | | dbfbe94d |
| example_overview.md | 19.7 kB | | a06efc40 |
| experimental_overview.html | 10.8 kB | | 2fc401e9 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | ce37a407 |
| gfpo.md | 5.24 kB | | 4f2c132c |
| gkd_trainer.html | 119 kB | | ea6009ff |
| gkd_trainer.md | 14.1 kB | | aeb9a573 |
| gold_trainer.html | 166 kB | | 05a61426 |
| gold_trainer.md | 18.1 kB | | 270d8f1d |
| grpo_trainer.html | 560 kB | | 1133324e |
| grpo_trainer.md | 55.4 kB | | 7fc4befd |
| grpo_with_replay_buffer.html | 89.6 kB | | a331b983 |
| grpo_with_replay_buffer.md | 6.16 kB | | c6337c03 |
| gspo_token.html | 50.2 kB | | 444ec7bf |
| gspo_token.md | 4.27 kB | | 1166410b |
| index.html | 29 kB | | c3ad1d0e |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | a14330f0 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 87c84a8e |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | 27b18ee7 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 137 kB | | f290ac2b |
| kto_trainer.md | 18.1 kB | | 140ec709 |
| liger_kernel_integration.html | 15 kB | | 0a7d24aa |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 836 kB | | 0efd5dd5 |
| llms.txt | 5 kB | | 56eb90bf |
| lora_without_regret.html | 45 kB | | c4c0b429 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | c128fc8a |
| merge_model_callback.md | 1.19 kB | | 5d76ecc5 |
| minillm_trainer.html | 179 kB | | 767ce68c |
| minillm_trainer.md | 16.4 kB | | 2e0d2e4d |
| nash_md_trainer.html | 124 kB | | b2cb3560 |
| nash_md_trainer.md | 16.3 kB | | 6a1fb541 |
| nemo_gym.html | 58.5 kB | | 0680e0c8 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.41 kB | | ef0a0bb0 |
| online_dpo_trainer.html | 179 kB | | 19e05f1f |
| online_dpo_trainer.md | 23.1 kB | | d223c68b |
| openenv.html | 114 kB | | 10e7ed9d |
| openenv.md | 27.8 kB | | 064dae84 |
| orpo_trainer.html | 127 kB | | 6bdd6532 |
| orpo_trainer.md | 17.7 kB | | 3b600f72 |
| paper_index.html | 734 kB | | 7a9cfbce |
| paper_index.md | 19.1 kB | | ddbe7def |
| papo_trainer.html | 111 kB | | ffe1c06f |
| papo_trainer.md | 8.82 kB | | 0a8a9a28 |
| peft_integration.html | 131 kB | | f8997c9d |
| peft_integration.md | 23.9 kB | | 529aba66 |
| ppo_trainer.html | 278 kB | | 9df51af3 |
| ppo_trainer.md | 41.4 kB | | 4dc4ef25 |
| prm_trainer.html | 117 kB | | 59895796 |
| prm_trainer.md | 13.9 kB | | 1c39b1bb |
| ptt_integration.html | 29.3 kB | | 46a35fe7 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 92d41fb8 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | 2c44d4d0 |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | 27230750 |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
| reward_trainer.html | 175 kB | | 54f113e2 |
| reward_trainer.md | 21.5 kB | | 54bdc721 |
|