| _app | | | 178 items |
| _toctree.yml | 3.31 kB | | 222c63dd |
| a2po_trainer.html | 102 kB | | 257157c9 |
| a2po_trainer.md | 16.7 kB | | 02482ceb |
| async_distillation_trainer.html | 173 kB | | e69caabe |
| async_distillation_trainer.md | 52.8 kB | | 9270ed7f |
| async_grpo_trainer.html | 214 kB | | fae6657b |
| async_grpo_trainer.md | 64.6 kB | | bba7e8cd |
| bema_for_reference_model.html | 91.5 kB | | 026b9318 |
| bema_for_reference_model.md | 7.12 kB | | 905020ec |
| callbacks.html | 97.5 kB | | 7b309693 |
| callbacks.md | 8.91 kB | | 6ec17da7 |
| chat_template_utils.html | 46 kB | | f743ff4e |
| chat_template_utils.md | 7.07 kB | | cf23f643 |
| chat_templates.html | 70.2 kB | | 9feca5f2 |
| chat_templates.md | 15 kB | | fad2df7c |
| clis.html | 53.9 kB | | ecea4df5 |
| clis.md | 12.9 kB | | 5e0a23e8 |
| community_tutorials.html | 30.8 kB | | 94b2c233 |
| community_tutorials.md | 11 kB | | ab326507 |
| cpo_trainer.html | 141 kB | | 7f4b3cd5 |
| cpo_trainer.md | 29.1 kB | | c76051cf |
| customization.html | 45.5 kB | | c476ad1f |
| customization.md | 7.5 kB | | 61430f91 |
| data_utils.html | 59.8 kB | | 793016e6 |
| data_utils.md | 7.28 kB | | 8544111d |
| dataset_formats.html | 190 kB | | c9ca95a9 |
| dataset_formats.md | 36.8 kB | | bc61402a |
| deepspeed_integration.html | 15.4 kB | | b946053b |
| deepspeed_integration.md | 1.46 kB | | 0c0b6c40 |
| distillation_trainer.html | 232 kB | | 2b95c964 |
| distillation_trainer.md | 40.3 kB | | bf99988c |
| distributing_training.html | 32.6 kB | | 4692d166 |
| distributing_training.md | 4.93 kB | | 2834266a |
| dpo_trainer.html | 238 kB | | e2f0d8fd |
| dpo_trainer.md | 46.9 kB | | 5e84187a |
| example_overview.html | 31.9 kB | | ea348168 |
| example_overview.md | 15.4 kB | | a4e72923 |
| 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 | | 06137c8d |
| gkd_trainer.md | 20.9 kB | | 03b0599c |
| gmpo.html | 89.2 kB | | 798575ab |
| gmpo.md | 13.7 kB | | db82e4de |
| gold_trainer.html | 192 kB | | 8d6ec3f9 |
| gold_trainer.md | 33.3 kB | | bc4f9a65 |
| grpo_trainer.html | 634 kB | | 48939fe1 |
| grpo_trainer.md | 114 kB | | 53e11932 |
| gspo_token.html | 49.6 kB | | c6aa5ea1 |
| gspo_token.md | 5.29 kB | | d3a9760d |
| harbor.html | 76.4 kB | | de799540 |
| harbor.md | 13.8 kB | | 703f60d3 |
| 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 | | 00d3e0ea |
| iw_opd_trainer.md | 21.4 kB | | 7d23c4f1 |
| 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 | | f6803544 |
| kto_trainer.md | 42.5 kB | | 56631100 |
| liger_kernel_integration.html | 15.6 kB | | e40b2f6f |
| liger_kernel_integration.md | 2.82 kB | | 14179541 |
| llms-full.txt | 1.31 MB | | 8b197517 |
| llms.txt | 5.01 kB | | a08c960e |
| long_context_training.html | 50.5 kB | | 0ebdb56a |
| long_context_training.md | 13.2 kB | | 989926e8 |
| lora_without_regret.html | 44.1 kB | | 8ce886aa |
| lora_without_regret.md | 14.3 kB | | e31f56a0 |
| merge_model_callback.html | 17.6 kB | | fede20e3 |
| merge_model_callback.md | 1.39 kB | | aee609e0 |
| minillm_trainer.html | 181 kB | | 88d24aca |
| minillm_trainer.md | 25.5 kB | | 7be1df9f |
| objects.inv | 2.22 kB | | a52dcc43 |
| online_dpo_trainer.html | 177 kB | | 0126f0a6 |
| online_dpo_trainer.md | 35.9 kB | | 5d54f8e7 |
| openenv.html | 135 kB | | d32202aa |
| openenv.md | 35.8 kB | | 3c8d69de |
| openreward.html | 70.4 kB | | a95a1950 |
| openreward.md | 11.9 kB | | f38499eb |
| orpo_trainer.html | 124 kB | | e7368696 |
| orpo_trainer.md | 23.7 kB | | 5258f265 |
| paper_index.html | 822 kB | | 28e6dc96 |
| paper_index.md | 92.5 kB | | 8673fe76 |
| peft_integration.html | 119 kB | | 01122243 |
| peft_integration.md | 21.9 kB | | acfc4b33 |
| 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 | | 4abebd9d |
| reducing_memory_usage.md | 14.3 kB | | 50881fa2 |
| reward_trainer.html | 179 kB | | 99057ed2 |
| reward_trainer.md | 31.6 kB | | ad7093e5 |
| rewards.html | 123 kB | | 570cd459 |
| rewards.md | 12.4 kB | | ddf84799 |
|