| _app | | | 137 items |
| _toctree.yml | 3.38 kB | | 9da8f3eb |
| async_grpo_trainer.html | 108 kB | | a5ddf9fc |
| async_grpo_trainer.md | 12.3 kB | | 1941d195 |
| bco_trainer.html | 130 kB | | 210f1a6f |
| bco_trainer.md | 14.1 kB | | e322872f |
| bema_for_reference_model.html | 90 kB | | 44a92726 |
| bema_for_reference_model.md | 7.18 kB | | 72031906 |
| callbacks.html | 95.8 kB | | 0e0e1f7d |
| callbacks.md | 7.88 kB | | 808ccc69 |
| chat_template_utils.html | 45.8 kB | | 2d2340e6 |
| chat_template_utils.md | 5.48 kB | | 92534e58 |
| chat_templates.html | 28.3 kB | | 184d4630 |
| chat_templates.md | 5.13 kB | | ea92d71c |
| clis.html | 53.4 kB | | 4a7f2560 |
| clis.md | 12.8 kB | | e31be33f |
| community_tutorials.html | 31 kB | | 90739787 |
| community_tutorials.md | 11 kB | | 1a976c71 |
| cpo_trainer.html | 144 kB | | b64f6bcd |
| cpo_trainer.md | 23 kB | | 2a1baa44 |
| customization.html | 31 kB | | c839bc29 |
| customization.md | 4.08 kB | | 884f15ba |
| data_utils.html | 62.7 kB | | 2a4c0eba |
| data_utils.md | 6.87 kB | | 4aab276e |
| dataset_formats.html | 223 kB | | 01ce806e |
| dataset_formats.md | 40.2 kB | | afd849be |
| deepspeed_integration.html | 15.8 kB | | c5a8330c |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | 880f8878 |
| distillation_trainer.md | 12.3 kB | | 2be55845 |
| distributing_training.html | 96.5 kB | | 0ee4e022 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | 73fd5c39 |
| dpo_trainer.md | 30.8 kB | | eea4858a |
| example_overview.html | 42.7 kB | | a5345261 |
| example_overview.md | 19.7 kB | | d344047a |
| experimental_overview.html | 10.8 kB | | ccd3494b |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | eed8cf92 |
| gfpo.md | 5.24 kB | | e492da07 |
| gkd_trainer.html | 119 kB | | a58f1e3b |
| gkd_trainer.md | 14.1 kB | | 74e4010a |
| gold_trainer.html | 166 kB | | ec8f494c |
| gold_trainer.md | 18.1 kB | | ea60af2a |
| grpo_trainer.html | 560 kB | | ff161226 |
| grpo_trainer.md | 55.8 kB | | 74c8f39d |
| grpo_with_replay_buffer.html | 89.6 kB | | ba0b75de |
| grpo_with_replay_buffer.md | 6.16 kB | | 5f05d7ba |
| gspo_token.html | 50.2 kB | | f8cd0921 |
| gspo_token.md | 4.27 kB | | 8835399a |
| index.html | 29 kB | | 07b78ce7 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 2962a39c |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 878df1ca |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | 310354e1 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 137 kB | | 564e5288 |
| kto_trainer.md | 18.4 kB | | 01c90d32 |
| liger_kernel_integration.html | 15 kB | | ab66b011 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 867 kB | | 0deffea9 |
| llms.txt | 5.15 kB | | f2f83902 |
| lora_without_regret.html | 45 kB | | 4253b42f |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 67e50bfe |
| merge_model_callback.md | 1.19 kB | | 30109d4c |
| minillm_trainer.html | 179 kB | | 037d90dc |
| minillm_trainer.md | 16.4 kB | | b5a7e554 |
| nash_md_trainer.html | 124 kB | | a871f62b |
| nash_md_trainer.md | 16.3 kB | | f3bd380a |
| nemo_gym.html | 58.5 kB | | ba15c305 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.45 kB | | 464bbea2 |
| online_dpo_trainer.html | 179 kB | | 56149c71 |
| online_dpo_trainer.md | 23.1 kB | | 225e9364 |
| openenv.html | 114 kB | | 54555d9e |
| openenv.md | 27.8 kB | | 7cd19497 |
| orpo_trainer.html | 127 kB | | 914be892 |
| orpo_trainer.md | 17.7 kB | | b345d306 |
| paper_index.html | 742 kB | | 3f67a2bf |
| paper_index.md | 19.1 kB | | 52cdd1c0 |
| papo_trainer.html | 111 kB | | 6d8a6f4b |
| papo_trainer.md | 8.82 kB | | cba84cf1 |
| peft_integration.html | 131 kB | | 904655c7 |
| peft_integration.md | 23.9 kB | | 2600b5e6 |
| ppo_trainer.html | 278 kB | | ed5fdff1 |
| ppo_trainer.md | 41.4 kB | | d1f10f81 |
| prm_trainer.html | 117 kB | | 99da436d |
| prm_trainer.md | 13.9 kB | | c3a66361 |
| ptt_integration.html | 29.3 kB | | 35a399ce |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 7ded1a2f |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 95.4 kB | | 1cd9bbb3 |
| rapidfire_integration.md | 17.7 kB | | 08fed5af |
| reducing_memory_usage.html | 52.4 kB | | 6f138e5e |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
|