| _app | | | 422 items |
| _toctree.yml | 3.38 kB | | 9da8f3eb |
| async_grpo_trainer.html | 108 kB | | c9383047 |
| async_grpo_trainer.md | 12.3 kB | | 773029a8 |
| bco_trainer.html | 130 kB | | 4807ef93 |
| bco_trainer.md | 14.2 kB | | 0e8724ca |
| bema_for_reference_model.html | 90 kB | | 82a621e4 |
| bema_for_reference_model.md | 7.18 kB | | 2554f42c |
| callbacks.html | 95.8 kB | | 593b91f2 |
| callbacks.md | 7.88 kB | | 663c8cda |
| chat_template_utils.html | 46.7 kB | | 90359815 |
| chat_template_utils.md | 5.87 kB | | 1aabc2e1 |
| chat_templates.html | 44.7 kB | | 6b1b0b2a |
| chat_templates.md | 8.74 kB | | 686d05a1 |
| clis.html | 53.4 kB | | 118b4b95 |
| clis.md | 12.8 kB | | 9102c185 |
| community_tutorials.html | 31 kB | | b03b469d |
| community_tutorials.md | 11 kB | | 3950953b |
| cpo_trainer.html | 145 kB | | 0680bfc8 |
| cpo_trainer.md | 23.2 kB | | 227625ae |
| customization.html | 31 kB | | bed0d0d3 |
| customization.md | 4.08 kB | | 52f3f187 |
| data_utils.html | 62.7 kB | | 91c606bd |
| data_utils.md | 6.87 kB | | 8b308ca1 |
| dataset_formats.html | 223 kB | | 94960760 |
| dataset_formats.md | 43 kB | | 45dcacfe |
| deepspeed_integration.html | 15.8 kB | | 6949abe4 |
| deepspeed_integration.md | 1.52 kB | | e5b0fad5 |
| distillation_trainer.html | 161 kB | | f59d1c67 |
| distillation_trainer.md | 12.3 kB | | 4f78174b |
| distributing_training.html | 96.5 kB | | 6c91e314 |
| distributing_training.md | 21 kB | | 75949925 |
| dpo_trainer.html | 233 kB | | 2a3d4992 |
| dpo_trainer.md | 31.1 kB | | fa6cb7c2 |
| example_overview.html | 42.8 kB | | 196797cb |
| example_overview.md | 19.7 kB | | f119b397 |
| experimental_overview.html | 10.8 kB | | ec5434b1 |
| experimental_overview.md | 1.62 kB | | 45d90cc6 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 85 kB | | e9e28a10 |
| gfpo.md | 5.24 kB | | ac14ce08 |
| gkd_trainer.html | 119 kB | | ee49c0a9 |
| gkd_trainer.md | 14.1 kB | | 4c240b8e |
| gold_trainer.html | 166 kB | | 502b784c |
| gold_trainer.md | 18.1 kB | | 546271e7 |
| grpo_trainer.html | 561 kB | | 62e0ab41 |
| grpo_trainer.md | 61.5 kB | | b0c2046c |
| grpo_with_replay_buffer.html | 90.3 kB | | 1dd25547 |
| grpo_with_replay_buffer.md | 6.16 kB | | b5f47f54 |
| gspo_token.html | 50.2 kB | | e387118e |
| gspo_token.md | 4.27 kB | | d189a3ef |
| index.html | 29 kB | | c0bee7a0 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 52ed52d3 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 7e64a0c1 |
| jobs_training.md | 6.46 kB | | cb814663 |
| kernels_hub.html | 26.8 kB | | fbbf948c |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 134 kB | | e0fcf280 |
| kto_trainer.md | 18.2 kB | | 95233a85 |
| liger_kernel_integration.html | 15 kB | | 56d7df2c |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 950 kB | | 0d75de74 |
| llms.txt | 5.15 kB | | 5b47a481 |
| lora_without_regret.html | 45 kB | | 176dc194 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | a2413166 |
| merge_model_callback.md | 1.19 kB | | e93bf6fb |
| minillm_trainer.html | 180 kB | | 8f7badcf |
| minillm_trainer.md | 16.4 kB | | b8c60c0b |
| nash_md_trainer.html | 125 kB | | bd98f9fc |
| nash_md_trainer.md | 16.6 kB | | 9b9b3442 |
| nemo_gym.html | 58.5 kB | | a1c86ec6 |
| nemo_gym.md | 10.3 kB | | 45caccd9 |
| objects.inv | 2.45 kB | | 066be50a |
| online_dpo_trainer.html | 180 kB | | 306223da |
| online_dpo_trainer.md | 23.3 kB | | 579d3f7f |
| openenv.html | 114 kB | | 4d0d00aa |
| openenv.md | 27.8 kB | | affaaa5b |
| orpo_trainer.html | 128 kB | | a8242705 |
| orpo_trainer.md | 17.9 kB | | 4ad0c5bf |
| paper_index.html | 761 kB | | f9be3158 |
| paper_index.md | 85.1 kB | | a6cbc0b9 |
| papo_trainer.html | 112 kB | | f6c1914a |
| papo_trainer.md | 8.82 kB | | d9080971 |
| peft_integration.html | 131 kB | | 86829ccb |
| peft_integration.md | 23.9 kB | | c00707d7 |
| ppo_trainer.html | 279 kB | | 5d68ea41 |
| ppo_trainer.md | 41.5 kB | | 943e8826 |
| prm_trainer.html | 118 kB | | 7f537898 |
| prm_trainer.md | 14.2 kB | | cb9f8291 |
| ptt_integration.html | 29.3 kB | | 8e1b2d38 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 0bd03a9c |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 95.4 kB | | 7eea06f5 |
| rapidfire_integration.md | 17.8 kB | | b0dd6d2b |
| reducing_memory_usage.html | 57.1 kB | | 1338cab8 |
| reducing_memory_usage.md | 13.7 kB | | 1983462d |
|