| _app | | | 294 items |
| _toctree.yml | 3.29 kB | | 4ea3f42b |
| async_grpo_trainer.html | 108 kB | | 83bb1ca7 |
| async_grpo_trainer.md | 12.3 kB | | 746726f5 |
| bco_trainer.html | 130 kB | | c2805ece |
| bco_trainer.md | 14.1 kB | | feb76acd |
| bema_for_reference_model.html | 90 kB | | 484a926a |
| bema_for_reference_model.md | 7.18 kB | | b3528009 |
| callbacks.html | 95.8 kB | | c656b7f1 |
| callbacks.md | 7.88 kB | | ba1b4dd2 |
| chat_template_utils.html | 43.9 kB | | 5149dd8a |
| chat_template_utils.md | 4.65 kB | | acdaacf5 |
| clis.html | 53.4 kB | | 9d9319ab |
| clis.md | 12.8 kB | | 31ea656b |
| community_tutorials.html | 31 kB | | 2177217d |
| community_tutorials.md | 11 kB | | e7838b59 |
| cpo_trainer.html | 144 kB | | ac25eca3 |
| cpo_trainer.md | 23 kB | | eb796506 |
| customization.html | 31 kB | | fb7d1e9c |
| customization.md | 4.08 kB | | 1e6e793b |
| data_utils.html | 62.9 kB | | 8f858ce0 |
| data_utils.md | 6.32 kB | | ccf36928 |
| dataset_formats.html | 223 kB | | fa3de6fc |
| dataset_formats.md | 40.2 kB | | d587c58e |
| deepspeed_integration.html | 15.8 kB | | 3539534c |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distributing_training.html | 96.5 kB | | ead4d286 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | a1f7a842 |
| dpo_trainer.md | 30.7 kB | | fd9226e1 |
| example_overview.html | 43.2 kB | | 13e361a5 |
| example_overview.md | 20.1 kB | | 0f9942e8 |
| experimental_overview.html | 10.8 kB | | 54189c52 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | 35eb6a91 |
| gfpo.md | 5.24 kB | | 48aafb8e |
| gkd_trainer.html | 119 kB | | 3c725892 |
| gkd_trainer.md | 14.1 kB | | 76911d24 |
| gold_trainer.html | 163 kB | | b5790761 |
| gold_trainer.md | 17.5 kB | | 37330e8d |
| grpo_trainer.html | 555 kB | | 7200f25f |
| grpo_trainer.md | 54 kB | | 07ce397e |
| grpo_with_replay_buffer.html | 89.6 kB | | ad776356 |
| grpo_with_replay_buffer.md | 6.16 kB | | 09fb0ca9 |
| gspo_token.html | 50.2 kB | | 193a243d |
| gspo_token.md | 4.27 kB | | 28d81571 |
| index.html | 29 kB | | f078fc57 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 572c6b92 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 4f74422e |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| judges.html | 122 kB | | 42d1416a |
| judges.md | 15.8 kB | | 206f41f9 |
| kernels_hub.html | 26.8 kB | | 6f8a412f |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 138 kB | | e31f7880 |
| kto_trainer.md | 19.4 kB | | 2e2c1617 |
| liger_kernel_integration.html | 15 kB | | 9c2d5b57 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 833 kB | | dac42174 |
| llms.txt | 5.04 kB | | 6cfd0250 |
| lora_without_regret.html | 45 kB | | 676305c4 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | ab0682e0 |
| merge_model_callback.md | 1.19 kB | | bc256b6d |
| minillm_trainer.html | 179 kB | | b0cc9827 |
| minillm_trainer.md | 16.4 kB | | 80648127 |
| nash_md_trainer.html | 130 kB | | 972d68e9 |
| nash_md_trainer.md | 17.1 kB | | 16c78342 |
| nemo_gym.html | 58.5 kB | | 3e8c1167 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.45 kB | | d7590e9d |
| online_dpo_trainer.html | 195 kB | | 297c92b8 |
| online_dpo_trainer.md | 26.3 kB | | 00b5eeb5 |
| openenv.html | 114 kB | | 3ee67e9d |
| openenv.md | 27.8 kB | | acd6b676 |
| orpo_trainer.html | 127 kB | | 12bfb692 |
| orpo_trainer.md | 17.7 kB | | 978c6d6f |
| paper_index.html | 732 kB | | e8cf07a7 |
| paper_index.md | 17 kB | | 34916cb3 |
| papo_trainer.html | 111 kB | | 2e79dfd6 |
| papo_trainer.md | 8.82 kB | | ff94ed3a |
| peft_integration.html | 131 kB | | 60428e5b |
| peft_integration.md | 23.9 kB | | 28a04292 |
| ppo_trainer.html | 280 kB | | cf3b0faa |
| ppo_trainer.md | 42 kB | | 64b50305 |
| prm_trainer.html | 117 kB | | a473f5a4 |
| prm_trainer.md | 13.9 kB | | fbeb00c2 |
| ptt_integration.html | 29.3 kB | | 5f40c385 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 2e29ee2d |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | 52c09586 |
| rapidfire_integration.md | 12.8 kB | | c14e6d99 |
| reducing_memory_usage.html | 52.4 kB | | 79a28b52 |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
| reward_trainer.html | 175 kB | | 17b554cc |
| reward_trainer.md | 21.5 kB | | e0c92c89 |
|