| _app | | | 145 items |
| _toctree.yml | 3.31 kB | | 222c63dd |
| a2po_trainer.html | 102 kB | | 2e3d59b1 |
| a2po_trainer.md | 16.7 kB | | b667ac5f |
| async_distillation_trainer.html | 173 kB | | 4c6fe7f4 |
| async_distillation_trainer.md | 52.8 kB | | 45a41acf |
| async_grpo_trainer.html | 214 kB | | 36014f33 |
| async_grpo_trainer.md | 64.6 kB | | 49350f16 |
| bema_for_reference_model.html | 91.5 kB | | c2c5f32b |
| bema_for_reference_model.md | 7.12 kB | | 8de79245 |
| callbacks.html | 97.5 kB | | f130cfee |
| callbacks.md | 8.91 kB | | 259cb0ce |
| chat_template_utils.html | 46 kB | | 10957386 |
| chat_template_utils.md | 7.07 kB | | 8039229d |
| chat_templates.html | 70.2 kB | | 63a8cf59 |
| chat_templates.md | 15 kB | | 622e10cc |
| clis.html | 53.9 kB | | 907bcf99 |
| clis.md | 12.9 kB | | 1181d9b7 |
| community_tutorials.html | 30.8 kB | | 66614c63 |
| community_tutorials.md | 11 kB | | 5854f52a |
| cpo_trainer.html | 141 kB | | 4ae78a91 |
| cpo_trainer.md | 29.1 kB | | 65d74f1d |
| customization.html | 45.5 kB | | 817b6a23 |
| customization.md | 7.5 kB | | e3c456c4 |
| data_utils.html | 59.8 kB | | 4795d8d7 |
| data_utils.md | 7.28 kB | | f87d555e |
| dataset_formats.html | 190 kB | | dc1cbe5d |
| dataset_formats.md | 36.8 kB | | 6e52a2db |
| deepspeed_integration.html | 15.4 kB | | b946053b |
| deepspeed_integration.md | 1.46 kB | | 0c0b6c40 |
| distillation_trainer.html | 232 kB | | e9e5b0d8 |
| distillation_trainer.md | 40.3 kB | | 29f2c8ab |
| distributing_training.html | 32.6 kB | | 4692d166 |
| distributing_training.md | 4.93 kB | | 2834266a |
| dpo_trainer.html | 238 kB | | 1375edd2 |
| dpo_trainer.md | 46.9 kB | | 56f9fa39 |
| example_overview.html | 31.9 kB | | b15fcb0e |
| example_overview.md | 15.4 kB | | 78caf620 |
| experimental_overview.html | 13.4 kB | | 9dd8f75f |
| experimental_overview.md | 3.04 kB | | 43e69c0b |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gkd_trainer.html | 118 kB | | 2791180c |
| gkd_trainer.md | 20.9 kB | | e4556889 |
| gmpo.html | 89.2 kB | | 00e927e3 |
| gmpo.md | 13.7 kB | | 30a0e9b4 |
| gold_trainer.html | 192 kB | | ffd1cec3 |
| gold_trainer.md | 33.3 kB | | 025bfa9b |
| grpo_trainer.html | 634 kB | | 839216ce |
| grpo_trainer.md | 114 kB | | d7cbd12b |
| gspo_token.html | 49.6 kB | | 45b1ca8b |
| gspo_token.md | 5.29 kB | | 75ac4aaa |
| harbor.html | 76.4 kB | | 837bbeb7 |
| harbor.md | 13.8 kB | | cb207d30 |
| index.html | 36.6 kB | | 43caeb61 |
| index.md | 4.57 kB | | f45595a7 |
| installation.html | 13.7 kB | | 900db346 |
| installation.md | 721 Bytes | | 93a212e0 |
| iw_opd_trainer.html | 143 kB | | b943d5bd |
| iw_opd_trainer.md | 21.4 kB | | 07b49895 |
| jobs_training.html | 58.7 kB | | d3f014a0 |
| jobs_training.md | 17.4 kB | | 12938320 |
| kernels_hub.html | 30.8 kB | | 845784fd |
| kernels_hub.md | 5.67 kB | | 9dc552d3 |
| kto_trainer.html | 220 kB | | 1e28299f |
| kto_trainer.md | 42.5 kB | | e7731356 |
| liger_kernel_integration.html | 15.6 kB | | 4a72ae6b |
| liger_kernel_integration.md | 2.82 kB | | 45ba7d59 |
| llms-full.txt | 1.31 MB | | 6fd30ec4 |
| llms.txt | 5.01 kB | | 6a39062b |
| long_context_training.html | 50.5 kB | | 1da2fd3f |
| long_context_training.md | 13.2 kB | | 5ca3ead8 |
| lora_without_regret.html | 44.1 kB | | 8ce886aa |
| lora_without_regret.md | 14.3 kB | | e31f56a0 |
| merge_model_callback.html | 17.6 kB | | 779d4a0c |
| merge_model_callback.md | 1.39 kB | | 6748170b |
| minillm_trainer.html | 181 kB | | e68136ba |
| minillm_trainer.md | 25.5 kB | | dad4b537 |
| objects.inv | 2.22 kB | | 14e88e9d |
| online_dpo_trainer.html | 177 kB | | 3b78990e |
| online_dpo_trainer.md | 35.9 kB | | 525955f8 |
| openenv.html | 135 kB | | 4be3a8c8 |
| openenv.md | 35.8 kB | | bb1c3741 |
| openreward.html | 70.4 kB | | 5ebe85f7 |
| openreward.md | 11.9 kB | | b3a5c1b8 |
| orpo_trainer.html | 124 kB | | a5a9a66a |
| orpo_trainer.md | 23.7 kB | | 578cf65e |
| paper_index.html | 822 kB | | c09c8a02 |
| paper_index.md | 92.5 kB | | 5cd75a1b |
| peft_integration.html | 119 kB | | 75f0e570 |
| peft_integration.md | 21.9 kB | | 21063976 |
| quickstart.html | 37.6 kB | | b8c77a45 |
| quickstart.md | 3.62 kB | | d6c66824 |
| rapidfire_integration.html | 94.2 kB | | 4bc2f89e |
| rapidfire_integration.md | 17.8 kB | | 337b5dbc |
| reducing_memory_usage.html | 59.5 kB | | 5cd68816 |
| reducing_memory_usage.md | 14.3 kB | | a7ecbce6 |
| reward_trainer.html | 179 kB | | e3272329 |
| reward_trainer.md | 31.6 kB | | fd9003ba |
| rewards.html | 123 kB | | c55a6a7f |
| rewards.md | 12.4 kB | | a517dc0e |
|