| _app | | | 133 items |
| _toctree.yml | 3.22 kB | | ca36b740 |
| async_grpo_trainer.html | 108 kB | | 75c85510 |
| async_grpo_trainer.md | 12.3 kB | | 3955e172 |
| bco_trainer.html | 131 kB | | bbcb5c2b |
| bco_trainer.md | 14.4 kB | | e4181d3c |
| bema_for_reference_model.html | 90 kB | | ef30607d |
| bema_for_reference_model.md | 7.18 kB | | b641f0f5 |
| callbacks.html | 95.8 kB | | a575931a |
| callbacks.md | 7.88 kB | | 9e0bb9fd |
| chat_template_utils.html | 43.9 kB | | 43d025b4 |
| chat_template_utils.md | 4.65 kB | | 67aca4c1 |
| clis.html | 53.4 kB | | bf72e732 |
| clis.md | 12.8 kB | | f6507af2 |
| community_tutorials.html | 31 kB | | 6c7dff18 |
| community_tutorials.md | 11 kB | | e405ed9b |
| cpo_trainer.html | 146 kB | | 1e4e64e9 |
| cpo_trainer.md | 23.2 kB | | 5e94fc0c |
| customization.html | 31 kB | | d9e234e0 |
| customization.md | 4.08 kB | | eaeb254c |
| data_utils.html | 62.9 kB | | b15d3d7d |
| data_utils.md | 6.32 kB | | 58fd161b |
| dataset_formats.html | 223 kB | | 1cec31a3 |
| dataset_formats.md | 40.2 kB | | ccd066fb |
| deepspeed_integration.html | 15.8 kB | | a4ecf989 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distributing_training.html | 96.5 kB | | 661e5547 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 231 kB | | c8b91860 |
| dpo_trainer.md | 30.6 kB | | c82785e5 |
| example_overview.html | 39.6 kB | | a6d16950 |
| example_overview.md | 19.5 kB | | 71ad338c |
| experimental_overview.html | 10.8 kB | | f315af99 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | 28c1fe48 |
| gfpo.md | 5.24 kB | | 1d036f30 |
| gkd_trainer.html | 119 kB | | 5590c6a1 |
| gkd_trainer.md | 14.1 kB | | c774ec52 |
| gold_trainer.html | 156 kB | | 3c4f5717 |
| gold_trainer.md | 16.8 kB | | 84089397 |
| grpo_trainer.html | 554 kB | | 14916886 |
| grpo_trainer.md | 53.8 kB | | fd15ca0f |
| grpo_with_replay_buffer.html | 89.6 kB | | 837257b5 |
| grpo_with_replay_buffer.md | 6.16 kB | | 47c99115 |
| gspo_token.html | 50.2 kB | | 391ca8ed |
| gspo_token.md | 4.27 kB | | 4f450c23 |
| index.html | 28.8 kB | | 75f394af |
| index.md | 3.68 kB | | 55bdb9e3 |
| installation.html | 13.9 kB | | b372539a |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 524546bd |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| judges.html | 122 kB | | 0ef209e1 |
| judges.md | 15.8 kB | | 78ba7d5b |
| kernels_hub.html | 26.8 kB | | 1b97f768 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 138 kB | | 4f16e2ac |
| kto_trainer.md | 19.4 kB | | 46a54998 |
| liger_kernel_integration.html | 15 kB | | 155344a4 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 809 kB | | 3c13a9ff |
| llms.txt | 4.91 kB | | 7a2a4857 |
| lora_without_regret.html | 45 kB | | 65cb6b6d |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | f7288017 |
| merge_model_callback.md | 1.19 kB | | 2bef46eb |
| minillm_trainer.html | 179 kB | | 8069b190 |
| minillm_trainer.md | 16.4 kB | | 1b2aa9e9 |
| nash_md_trainer.html | 130 kB | | 61089b02 |
| nash_md_trainer.md | 17.1 kB | | be74ef20 |
| nemo_gym.html | 58.5 kB | | 7321c17f |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.37 kB | | 607a77f2 |
| online_dpo_trainer.html | 195 kB | | 8e43a52c |
| online_dpo_trainer.md | 26.3 kB | | 01ad0790 |
| openenv.html | 88.2 kB | | 994b9769 |
| openenv.md | 25.4 kB | | 7d5f9953 |
| orpo_trainer.html | 129 kB | | 46bf4326 |
| orpo_trainer.md | 17.9 kB | | c439f6d8 |
| paper_index.html | 717 kB | | c0e0981c |
| paper_index.md | 13.8 kB | | 522d6217 |
| papo_trainer.html | 111 kB | | 3f430050 |
| papo_trainer.md | 8.82 kB | | d145653a |
| peft_integration.html | 131 kB | | cfcd5c06 |
| peft_integration.md | 23.9 kB | | 45135615 |
| ppo_trainer.html | 280 kB | | 2a517416 |
| ppo_trainer.md | 42 kB | | a6780e46 |
| prm_trainer.html | 117 kB | | bfee1cbf |
| prm_trainer.md | 13.9 kB | | 0060fd29 |
| ptt_integration.html | 29.3 kB | | 68d2e9ed |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 7ff44865 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | a1824bb9 |
| rapidfire_integration.md | 12.8 kB | | c14e6d99 |
| reducing_memory_usage.html | 52.4 kB | | 62612685 |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
| reward_trainer.html | 175 kB | | b5d207f8 |
| reward_trainer.md | 21.5 kB | | 807667ae |
|