| _app | | | 337 items |
| _toctree.yml | 3.38 kB | | 9da8f3eb |
| async_grpo_trainer.html | 108 kB | | eff45115 |
| async_grpo_trainer.md | 12.3 kB | | ab1eda44 |
| bco_trainer.html | 130 kB | | 5d189347 |
| bco_trainer.md | 14.1 kB | | c4f9efb9 |
| bema_for_reference_model.html | 90 kB | | f929beb2 |
| bema_for_reference_model.md | 7.18 kB | | afe95e52 |
| callbacks.html | 95.8 kB | | f651ae34 |
| callbacks.md | 7.88 kB | | 77a10d62 |
| chat_template_utils.html | 45.8 kB | | d69fe433 |
| chat_template_utils.md | 5.48 kB | | 1bc987be |
| chat_templates.html | 28.3 kB | | 4dcf6be7 |
| chat_templates.md | 5.13 kB | | 1c79b8a8 |
| clis.html | 53.4 kB | | 67c3a285 |
| clis.md | 12.8 kB | | d1043853 |
| community_tutorials.html | 31 kB | | eca740a2 |
| community_tutorials.md | 11 kB | | d9016036 |
| cpo_trainer.html | 144 kB | | 7e55db7e |
| cpo_trainer.md | 23 kB | | 4ea1f6de |
| customization.html | 31 kB | | 182dda53 |
| customization.md | 4.08 kB | | 820ebc3e |
| data_utils.html | 62.7 kB | | 87f5acac |
| data_utils.md | 6.87 kB | | 65bd4ab8 |
| dataset_formats.html | 223 kB | | a8fa4ac3 |
| dataset_formats.md | 40.2 kB | | 1af34b25 |
| deepspeed_integration.html | 15.8 kB | | 59647267 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | 7f23ff3f |
| distillation_trainer.md | 12.3 kB | | 54fda472 |
| distributing_training.html | 96.5 kB | | 07dfac89 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | 7122b263 |
| dpo_trainer.md | 30.8 kB | | cc64c141 |
| example_overview.html | 42.7 kB | | 4f7d4eee |
| example_overview.md | 19.7 kB | | 84359455 |
| experimental_overview.html | 10.8 kB | | 739be21e |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | 9a539a29 |
| gfpo.md | 5.24 kB | | b651d5a2 |
| gkd_trainer.html | 119 kB | | 9b932c3d |
| gkd_trainer.md | 14.1 kB | | 54031999 |
| gold_trainer.html | 166 kB | | ec291cd3 |
| gold_trainer.md | 18.1 kB | | 424efbbb |
| grpo_trainer.html | 560 kB | | edf7eb6f |
| grpo_trainer.md | 55.8 kB | | 4dbe9954 |
| grpo_with_replay_buffer.html | 89.6 kB | | 0f4f2635 |
| grpo_with_replay_buffer.md | 6.16 kB | | 6b40a906 |
| gspo_token.html | 50.2 kB | | 01796fda |
| gspo_token.md | 4.27 kB | | fb5fbd40 |
| index.html | 29 kB | | 1feb4d9c |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 05d093ed |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 76025719 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | 8152d458 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 137 kB | | 4b814ef9 |
| kto_trainer.md | 18.4 kB | | c5111f22 |
| liger_kernel_integration.html | 15 kB | | 5255fa6b |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 862 kB | | 668d3a4a |
| llms.txt | 5.15 kB | | 1daeec6d |
| lora_without_regret.html | 45 kB | | 08e0bf24 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 7bac24bb |
| merge_model_callback.md | 1.19 kB | | 83660922 |
| minillm_trainer.html | 179 kB | | 0bbb99bc |
| minillm_trainer.md | 16.4 kB | | 688324f3 |
| nash_md_trainer.html | 124 kB | | 37a3011c |
| nash_md_trainer.md | 16.3 kB | | b2957c0f |
| nemo_gym.html | 58.5 kB | | 5d6972f3 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.45 kB | | 05423ff2 |
| online_dpo_trainer.html | 179 kB | | c40e8c3b |
| online_dpo_trainer.md | 23.1 kB | | 118a40d7 |
| openenv.html | 114 kB | | 5433321d |
| openenv.md | 27.8 kB | | cf404345 |
| orpo_trainer.html | 127 kB | | 10e8531b |
| orpo_trainer.md | 17.7 kB | | d90e3f83 |
| paper_index.html | 742 kB | | ce9ebf7b |
| paper_index.md | 19.1 kB | | d7df0041 |
| papo_trainer.html | 111 kB | | babd3b91 |
| papo_trainer.md | 8.82 kB | | 3db7d86e |
| peft_integration.html | 131 kB | | c24389bc |
| peft_integration.md | 23.9 kB | | b2584fb6 |
| ppo_trainer.html | 278 kB | | e4d5be31 |
| ppo_trainer.md | 41.4 kB | | 99114370 |
| prm_trainer.html | 117 kB | | 93851461 |
| prm_trainer.md | 13.9 kB | | e647aa14 |
| ptt_integration.html | 29.3 kB | | af0effb8 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | c403e06b |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | 4f565992 |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | 4ee94d73 |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
|