| _app | | | 467 items |
| _toctree.yml | 3.14 kB | | 0bf3961a |
| bco_trainer.html | 142 kB | | 2362f527 |
| bco_trainer.md | 14.3 kB | | 74872526 |
| bema_for_reference_model.html | 91.3 kB | | 5bd74062 |
| bema_for_reference_model.md | 7.7 kB | | a62dd7ba |
| callbacks.html | 101 kB | | 13ab34a4 |
| callbacks.md | 8.14 kB | | 61cc264c |
| chat_template_utils.html | 69.1 kB | | 62efe7ba |
| chat_template_utils.md | 7.22 kB | | bc3431df |
| clis.html | 53.4 kB | | c5e06d0a |
| clis.md | 12.8 kB | | f80e1162 |
| community_tutorials.html | 31 kB | | b739da88 |
| community_tutorials.md | 10.9 kB | | 5f52621d |
| cpo_trainer.html | 154 kB | | 884411da |
| cpo_trainer.md | 22.9 kB | | bc54f35e |
| customization.html | 37.4 kB | | 0a3c04d7 |
| customization.md | 4.9 kB | | 6f7964d9 |
| data_utils.html | 177 kB | | 969067f7 |
| data_utils.md | 18.9 kB | | 77518bde |
| dataset_formats.html | 219 kB | | 1a47a049 |
| dataset_formats.md | 41.2 kB | | 772bed08 |
| deepspeed_integration.html | 15.9 kB | | 40d87ab6 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distributing_training.html | 80.9 kB | | e1b047cb |
| distributing_training.md | 18.8 kB | | 3b39fd9e |
| dpo_trainer.html | 251 kB | | 942f60fc |
| dpo_trainer.md | 35.4 kB | | 91d41d00 |
| example_overview.html | 42.8 kB | | f3691eff |
| example_overview.md | 16.1 kB | | a1af6fd7 |
| experimental_overview.html | 10.8 kB | | 7b5a617c |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 89.4 kB | | 201e6088 |
| gfpo.md | 5.35 kB | | 49a8501a |
| gkd_trainer.html | 123 kB | | 22971244 |
| gkd_trainer.md | 13.9 kB | | eede795c |
| gold_trainer.html | 144 kB | | 6df1bbbf |
| gold_trainer.md | 13.8 kB | | 04c14b32 |
| grpo_trainer.html | 536 kB | | eb90e360 |
| grpo_trainer.md | 48.8 kB | | ffdddb67 |
| grpo_with_replay_buffer.html | 94.7 kB | | 909ebffd |
| grpo_with_replay_buffer.md | 6.27 kB | | a2fe07db |
| gspo_token.html | 50.6 kB | | cf291064 |
| gspo_token.md | 4.38 kB | | 312335c9 |
| index.html | 34.5 kB | | 0029f8b2 |
| index.md | 3.03 kB | | f9223a7e |
| installation.html | 18.4 kB | | 8d3b8fb6 |
| installation.md | 1.9 kB | | adbd95bf |
| jobs_training.html | 32.9 kB | | b4980df6 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| judges.html | 119 kB | | 88f75b25 |
| judges.md | 15 kB | | 4b9bcf46 |
| kernels_hub.html | 26.8 kB | | 8e9a1d17 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 159 kB | | 00aff03f |
| kto_trainer.md | 20.7 kB | | 51888b1e |
| liger_kernel_integration.html | 15 kB | | 39fc6768 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 819 kB | | b12dec68 |
| llms.txt | 4.76 kB | | 039238ea |
| lora_without_regret.html | 45.1 kB | | 67c1aec4 |
| lora_without_regret.md | 14.5 kB | | 38851bd7 |
| merge_model_callback.html | 17.8 kB | | 13b28fc0 |
| merge_model_callback.md | 1.19 kB | | 522f2663 |
| minillm_trainer.html | 184 kB | | 09173498 |
| minillm_trainer.md | 16.5 kB | | f4f341a9 |
| model_utils.html | 40.7 kB | | b7669634 |
| model_utils.md | 3.42 kB | | 63b9bd58 |
| models.html | 128 kB | | aa515292 |
| models.md | 14.7 kB | | 80ff5658 |
| nash_md_trainer.html | 134 kB | | 453166c7 |
| nash_md_trainer.md | 16.7 kB | | f483d6dc |
| objects.inv | 2.57 kB | | efd0e24f |
| online_dpo_trainer.html | 195 kB | | c25da950 |
| online_dpo_trainer.md | 25.5 kB | | 05f46a1f |
| openenv.html | 86.6 kB | | e35a0c9b |
| openenv.md | 25.1 kB | | 4b1216f4 |
| orpo_trainer.html | 136 kB | | 345293de |
| orpo_trainer.md | 17.6 kB | | 453efe0a |
| others.html | 29.7 kB | | 3902ea08 |
| others.md | 2.18 kB | | 9d428366 |
| paper_index.html | 455 kB | | e7b9c392 |
| paper_index.md | 28.1 kB | | 8f95c37c |
| papo_trainer.html | 116 kB | | 2d261a88 |
| papo_trainer.md | 8.83 kB | | 260331c9 |
| peft_integration.html | 131 kB | | f15c792c |
| peft_integration.md | 23.8 kB | | 575f6bb6 |
| ppo_trainer.html | 284 kB | | c0071975 |
| ppo_trainer.md | 41.3 kB | | 24ce0ae6 |
| prm_trainer.html | 123 kB | | 7064f3ef |
| prm_trainer.md | 13.7 kB | | 42310642 |
| quickstart.html | 41 kB | | 1ac70c00 |
| quickstart.md | 4.02 kB | | 4c70d618 |
| rapidfire_integration.html | 81.2 kB | | 13f9fca1 |
| rapidfire_integration.md | 12.8 kB | | 33fdfe4a |
| reducing_memory_usage.html | 52.7 kB | | 91424fb1 |
| reducing_memory_usage.md | 11.7 kB | | 5aa280c3 |
| reward_trainer.html | 199 kB | | d8924575 |
| reward_trainer.md | 23.7 kB | | 99df4988 |
|