| _app | | | 137 items |
| _toctree.yml | 3.38 kB | | 9da8f3eb |
| async_grpo_trainer.html | 108 kB | | 7bd7e2e3 |
| async_grpo_trainer.md | 12.3 kB | | e4a79390 |
| bco_trainer.html | 130 kB | | 3620c900 |
| bco_trainer.md | 14.1 kB | | 7703310c |
| bema_for_reference_model.html | 90 kB | | 3f083b62 |
| bema_for_reference_model.md | 7.18 kB | | a61d008a |
| callbacks.html | 95.8 kB | | 4a84ec98 |
| callbacks.md | 7.88 kB | | 190881f9 |
| chat_template_utils.html | 45.8 kB | | 19de945a |
| chat_template_utils.md | 5.48 kB | | 731b9cc6 |
| chat_templates.html | 28.3 kB | | f42ad5b8 |
| chat_templates.md | 5.13 kB | | 6bafdc0c |
| clis.html | 53.4 kB | | d745340f |
| clis.md | 12.8 kB | | f8072ab4 |
| community_tutorials.html | 31 kB | | fce2f40e |
| community_tutorials.md | 11 kB | | 04d867fd |
| cpo_trainer.html | 144 kB | | 90183869 |
| cpo_trainer.md | 23 kB | | da818a7b |
| customization.html | 31 kB | | 3998d108 |
| customization.md | 4.08 kB | | ba9a79d9 |
| data_utils.html | 62.7 kB | | 0d09793f |
| data_utils.md | 6.87 kB | | 5baf2218 |
| dataset_formats.html | 223 kB | | 420bf6be |
| dataset_formats.md | 40.2 kB | | 238a9a3c |
| deepspeed_integration.html | 15.8 kB | | 39a8d9fd |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | 7c483cb8 |
| distillation_trainer.md | 12.3 kB | | 28479e6e |
| distributing_training.html | 96.5 kB | | 2a0256cb |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | 338afb94 |
| dpo_trainer.md | 30.8 kB | | 42338cb9 |
| example_overview.html | 42.7 kB | | 0df553b8 |
| example_overview.md | 19.7 kB | | 1e9c9a2c |
| experimental_overview.html | 10.8 kB | | 75d18e5f |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | 70012539 |
| gfpo.md | 5.24 kB | | 9545564f |
| gkd_trainer.html | 119 kB | | f28fd71d |
| gkd_trainer.md | 14.1 kB | | ccaec6a5 |
| gold_trainer.html | 166 kB | | 7de01ed7 |
| gold_trainer.md | 18.1 kB | | 7183229f |
| grpo_trainer.html | 560 kB | | 6101c489 |
| grpo_trainer.md | 55.8 kB | | cf30be2f |
| grpo_with_replay_buffer.html | 89.6 kB | | f9ce2361 |
| grpo_with_replay_buffer.md | 6.16 kB | | c410d852 |
| gspo_token.html | 50.2 kB | | 5ed338ea |
| gspo_token.md | 4.27 kB | | da32df4c |
| index.html | 29 kB | | 57b18b03 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 8fc3caa2 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | a06b763b |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | 6d282ebc |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 137 kB | | 0a783937 |
| kto_trainer.md | 18.4 kB | | 55be5644 |
| liger_kernel_integration.html | 15 kB | | 033f6486 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 862 kB | | 2d25e647 |
| llms.txt | 5.15 kB | | 4ff88b2a |
| lora_without_regret.html | 45 kB | | 3b9d7345 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | faa7ea44 |
| merge_model_callback.md | 1.19 kB | | 3b9c0641 |
| minillm_trainer.html | 179 kB | | f574c613 |
| minillm_trainer.md | 16.4 kB | | a9ba42e6 |
| nash_md_trainer.html | 124 kB | | 6b3eb185 |
| nash_md_trainer.md | 16.3 kB | | a28b84ab |
| nemo_gym.html | 58.5 kB | | ac530556 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.45 kB | | 7876cb6c |
| online_dpo_trainer.html | 179 kB | | 529f5106 |
| online_dpo_trainer.md | 23.1 kB | | 2c0fa419 |
| openenv.html | 114 kB | | 77c0fc85 |
| openenv.md | 27.8 kB | | d468c8b3 |
| orpo_trainer.html | 127 kB | | c9f88e7b |
| orpo_trainer.md | 17.7 kB | | 2040a60c |
| paper_index.html | 742 kB | | 58517e27 |
| paper_index.md | 19.1 kB | | fd7b37b1 |
| papo_trainer.html | 111 kB | | 836bd257 |
| papo_trainer.md | 8.82 kB | | 5bfc6a69 |
| peft_integration.html | 131 kB | | fae20c3f |
| peft_integration.md | 23.9 kB | | 16c73904 |
| ppo_trainer.html | 278 kB | | 7f0be69d |
| ppo_trainer.md | 41.4 kB | | dd4de19c |
| prm_trainer.html | 117 kB | | e9ad1b6e |
| prm_trainer.md | 13.9 kB | | 6afd1a5a |
| ptt_integration.html | 29.3 kB | | fcf2dc08 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | eb0fdbb7 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | c7e3d573 |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | ff696d4d |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
|