| _app | | | 153 items |
| _toctree.yml | 3.21 kB | | ae39baa5 |
| bco_trainer.html | 131 kB | | 1d93edc2 |
| bco_trainer.md | 13.8 kB | | 0bfa8aa4 |
| bema_for_reference_model.html | 89.7 kB | | 73a83773 |
| bema_for_reference_model.md | 7.42 kB | | 493fefe8 |
| callbacks.html | 101 kB | | 81e56979 |
| callbacks.md | 8.14 kB | | 08412232 |
| chat_template_utils.html | 69 kB | | a0aaac74 |
| chat_template_utils.md | 7.22 kB | | 729a7f07 |
| clis.html | 53.4 kB | | 6d7e60b9 |
| clis.md | 12.8 kB | | f0a9eedf |
| community_tutorials.html | 31 kB | | 254649d8 |
| community_tutorials.md | 10.9 kB | | 9918e248 |
| cpo_trainer.html | 145 kB | | 52f69d44 |
| cpo_trainer.md | 22.6 kB | | 5eba9819 |
| customization.html | 37.4 kB | | 44b33ee7 |
| customization.md | 4.9 kB | | ef05ea3d |
| data_utils.html | 177 kB | | 2f0a90dd |
| data_utils.md | 18.9 kB | | 353edaa8 |
| dataset_formats.html | 219 kB | | 7ef8378e |
| dataset_formats.md | 41.2 kB | | 6b257d3b |
| deepspeed_integration.html | 15.8 kB | | 055d0131 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distributing_training.html | 80.8 kB | | c41e6688 |
| distributing_training.md | 18.7 kB | | 374f883e |
| dpo_trainer.html | 243 kB | | d82b79ad |
| dpo_trainer.md | 35.2 kB | | 2b1213f3 |
| example_overview.html | 36.4 kB | | b90de15b |
| example_overview.md | 16.8 kB | | c7ede7a5 |
| experimental_overview.html | 10.8 kB | | 41cbc545 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 82.8 kB | | 7f79e260 |
| gfpo.md | 5.06 kB | | 532016ff |
| gkd_trainer.html | 116 kB | | 5fd41502 |
| gkd_trainer.md | 13.7 kB | | 2cde0f45 |
| gold_trainer.html | 150 kB | | 8ff40878 |
| gold_trainer.md | 15.4 kB | | 4ab6cf51 |
| grpo_trainer.html | 534 kB | | e7cfae63 |
| grpo_trainer.md | 48.8 kB | | bbab44b3 |
| grpo_with_replay_buffer.html | 88.1 kB | | ccada6be |
| grpo_with_replay_buffer.md | 5.99 kB | | 8216c6e6 |
| gspo_token.html | 49 kB | | 544b2101 |
| gspo_token.md | 4.1 kB | | e746a3ca |
| index.html | 28.6 kB | | f6d693c2 |
| index.md | 3.68 kB | | a08ded5f |
| installation.html | 13.9 kB | | 1e1cb93e |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 0b3c6639 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| judges.html | 119 kB | | 263cee20 |
| judges.md | 15 kB | | 6c855e0e |
| kernels_hub.html | 26.8 kB | | 1564ce5c |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 136 kB | | 1a6ab5cb |
| kto_trainer.md | 18.8 kB | | 84dddab2 |
| liger_kernel_integration.html | 15 kB | | 1771bca4 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 822 kB | | 9a447ba7 |
| llms.txt | 4.86 kB | | a7dee8ed |
| lora_without_regret.html | 45.1 kB | | 4e1f5ad6 |
| lora_without_regret.md | 14.5 kB | | 1d6262a4 |
| merge_model_callback.html | 17.8 kB | | c5e46153 |
| merge_model_callback.md | 1.19 kB | | f2fedc72 |
| minillm_trainer.html | 178 kB | | 3c62088f |
| minillm_trainer.md | 16.3 kB | | cab9670b |
| model_utils.html | 40.6 kB | | 9a482dad |
| model_utils.md | 3.42 kB | | d925e669 |
| nash_md_trainer.html | 127 kB | | fb49540a |
| nash_md_trainer.md | 16.5 kB | | e5e0170b |
| objects.inv | 2.58 kB | | 1e34ae19 |
| online_dpo_trainer.html | 190 kB | | bd4bd14a |
| online_dpo_trainer.md | 25.2 kB | | 37e61975 |
| openenv.html | 87.8 kB | | 6fb2eda7 |
| openenv.md | 25.2 kB | | 8fc9ae06 |
| orpo_trainer.html | 127 kB | | b40a64be |
| orpo_trainer.md | 17.2 kB | | 9c3d298b |
| others.html | 29.7 kB | | 2152d1ce |
| others.md | 2.18 kB | | e392505d |
| paper_index.html | 559 kB | | d69f01b2 |
| paper_index.md | 31.8 kB | | 1697e02a |
| papo_trainer.html | 110 kB | | e8824311 |
| papo_trainer.md | 8.65 kB | | 7bf5cef4 |
| peft_integration.html | 131 kB | | 062d9658 |
| peft_integration.md | 23.8 kB | | 575f6bb6 |
| ppo_trainer.html | 278 kB | | 4da38062 |
| ppo_trainer.md | 41.3 kB | | 03b533c0 |
| prm_trainer.html | 116 kB | | 906ad6bc |
| prm_trainer.md | 13.5 kB | | 276b7ccc |
| ptt_integration.html | 29.3 kB | | 3fcf1edd |
| ptt_integration.md | 4.22 kB | | 4ea19a56 |
| quickstart.html | 37.7 kB | | 13a55a28 |
| quickstart.md | 3.36 kB | | 1a8bc789 |
| rapidfire_integration.html | 81.2 kB | | b4519166 |
| rapidfire_integration.md | 12.8 kB | | 33fdfe4a |
| reducing_memory_usage.html | 52.8 kB | | 64078d39 |
| reducing_memory_usage.md | 11.7 kB | | d9988a64 |
| reward_trainer.html | 192 kB | | cf41b69e |
| reward_trainer.md | 23.5 kB | | 63daa07b |
|