| _app | | | 170 items |
| _toctree.yml | 3.38 kB | | 9da8f3eb |
| async_grpo_trainer.html | 108 kB | | 215dc33d |
| async_grpo_trainer.md | 12.3 kB | | fc889363 |
| bco_trainer.html | 130 kB | | 67c3ca14 |
| bco_trainer.md | 14.1 kB | | 3e024961 |
| bema_for_reference_model.html | 90 kB | | 33daace1 |
| bema_for_reference_model.md | 7.18 kB | | 1fa1ac84 |
| callbacks.html | 95.8 kB | | 29345943 |
| callbacks.md | 7.88 kB | | 02c286f0 |
| chat_template_utils.html | 46.2 kB | | 31754a68 |
| chat_template_utils.md | 5.76 kB | | 4fa80621 |
| chat_templates.html | 33.5 kB | | 3b18d877 |
| chat_templates.md | 6.03 kB | | 0a22bd70 |
| clis.html | 53.4 kB | | 90d8e4aa |
| clis.md | 12.8 kB | | 8bd9af95 |
| community_tutorials.html | 31 kB | | f834b8b8 |
| community_tutorials.md | 11 kB | | fc2648e4 |
| cpo_trainer.html | 144 kB | | e0bde27d |
| cpo_trainer.md | 23 kB | | 6ec2bed2 |
| customization.html | 31 kB | | 0c6fef7a |
| customization.md | 4.08 kB | | f8318cc2 |
| data_utils.html | 62.7 kB | | fcd40f6a |
| data_utils.md | 6.87 kB | | c39cce79 |
| dataset_formats.html | 223 kB | | 6ea99341 |
| dataset_formats.md | 40.2 kB | | 196964e4 |
| deepspeed_integration.html | 15.8 kB | | eb1d4e07 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 161 kB | | 33c96c29 |
| distillation_trainer.md | 12.3 kB | | 905db2c9 |
| distributing_training.html | 96.5 kB | | 9d7cc540 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 233 kB | | 2145f55f |
| dpo_trainer.md | 30.8 kB | | daeecb95 |
| example_overview.html | 42.7 kB | | 9e10e5a6 |
| example_overview.md | 19.7 kB | | 4b9c755d |
| experimental_overview.html | 10.8 kB | | bd08856b |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 85 kB | | f8161082 |
| gfpo.md | 5.24 kB | | af037beb |
| gkd_trainer.html | 119 kB | | 69d37022 |
| gkd_trainer.md | 14.1 kB | | c5911ee6 |
| gold_trainer.html | 166 kB | | da5e7d47 |
| gold_trainer.md | 18.1 kB | | 1fd9a513 |
| grpo_trainer.html | 561 kB | | 46a2a1e4 |
| grpo_trainer.md | 55.8 kB | | ffb8975f |
| grpo_with_replay_buffer.html | 90.3 kB | | 37c7eae5 |
| grpo_with_replay_buffer.md | 6.16 kB | | 249be182 |
| gspo_token.html | 50.2 kB | | 954c92a8 |
| gspo_token.md | 4.27 kB | | df02de3d |
| index.html | 29 kB | | f807cb7a |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | d652db97 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | d6175a71 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | bcf380aa |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 138 kB | | ecffc6df |
| kto_trainer.md | 18.3 kB | | 07228974 |
| liger_kernel_integration.html | 15 kB | | d0be430c |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 868 kB | | f5960e17 |
| llms.txt | 5.15 kB | | b5b9e578 |
| lora_without_regret.html | 45 kB | | 96b0f5ae |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 9e027817 |
| merge_model_callback.md | 1.19 kB | | 22d68ced |
| minillm_trainer.html | 180 kB | | dc9727bb |
| minillm_trainer.md | 16.4 kB | | 6c0be76c |
| nash_md_trainer.html | 125 kB | | 99093561 |
| nash_md_trainer.md | 16.3 kB | | c69207d4 |
| nemo_gym.html | 58.5 kB | | 91e532bf |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.45 kB | | 2dd19954 |
| online_dpo_trainer.html | 180 kB | | 0a50c392 |
| online_dpo_trainer.md | 23.1 kB | | 5be63a05 |
| openenv.html | 114 kB | | 0d115fbe |
| openenv.md | 27.8 kB | | 93230968 |
| orpo_trainer.html | 127 kB | | 393dc802 |
| orpo_trainer.md | 17.7 kB | | 44d7e0b4 |
| paper_index.html | 742 kB | | 9cee8def |
| paper_index.md | 19.1 kB | | a3b883c5 |
| papo_trainer.html | 112 kB | | 515fb465 |
| papo_trainer.md | 8.82 kB | | f5106c36 |
| peft_integration.html | 131 kB | | 718e0c0f |
| peft_integration.md | 23.9 kB | | d27cd605 |
| ppo_trainer.html | 279 kB | | 1c0bb84f |
| ppo_trainer.md | 41.4 kB | | b7c067c3 |
| prm_trainer.html | 118 kB | | efea13cf |
| prm_trainer.md | 13.9 kB | | e2e16d6c |
| ptt_integration.html | 29.3 kB | | 2149d647 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 70896ab5 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 95.4 kB | | 838a975f |
| rapidfire_integration.md | 17.7 kB | | 08fed5af |
| reducing_memory_usage.html | 52.4 kB | | 9712abe6 |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
|