| _app | | | 135 items |
| _toctree.yml | 3.29 kB | | 3ae9d845 |
| async_grpo_trainer.html | 108 kB | | c96edaea |
| async_grpo_trainer.md | 12.3 kB | | 77993be5 |
| bco_trainer.html | 130 kB | | 568c35f0 |
| bco_trainer.md | 14.1 kB | | bf198248 |
| bema_for_reference_model.html | 90 kB | | 3aa5e9c5 |
| bema_for_reference_model.md | 7.18 kB | | f6962d7c |
| callbacks.html | 95.8 kB | | 5c5e701e |
| callbacks.md | 7.88 kB | | 2c07773f |
| chat_template_utils.html | 45.5 kB | | bde15012 |
| chat_template_utils.md | 5.3 kB | | 6824825b |
| clis.html | 53.4 kB | | d3fd54ed |
| clis.md | 12.8 kB | | 94ca449d |
| community_tutorials.html | 31 kB | | 8a3ab49d |
| community_tutorials.md | 11 kB | | 7761aca3 |
| cpo_trainer.html | 144 kB | | ea09eb13 |
| cpo_trainer.md | 23 kB | | 81df6ec5 |
| customization.html | 31 kB | | 114a92e7 |
| customization.md | 4.08 kB | | 283f338e |
| data_utils.html | 62.9 kB | | 0ed11d63 |
| data_utils.md | 6.32 kB | | 16623f3f |
| dataset_formats.html | 223 kB | | 312af34a |
| dataset_formats.md | 40.2 kB | | 15179b55 |
| deepspeed_integration.html | 15.8 kB | | b91cc408 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | 6775f23f |
| distillation_trainer.md | 12.3 kB | | d97fa14a |
| distributing_training.html | 96.5 kB | | 923bbac3 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | 13282bd8 |
| dpo_trainer.md | 30.8 kB | | 7eafa590 |
| example_overview.html | 42.7 kB | | 2257a995 |
| example_overview.md | 19.7 kB | | 1d591cb1 |
| experimental_overview.html | 10.8 kB | | f718be00 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | c5d0e2c6 |
| gfpo.md | 5.24 kB | | e5cf0060 |
| gkd_trainer.html | 119 kB | | ec7e3081 |
| gkd_trainer.md | 14.1 kB | | 934f2bf8 |
| gold_trainer.html | 166 kB | | e07ea6b9 |
| gold_trainer.md | 18.1 kB | | 92c9b62d |
| grpo_trainer.html | 560 kB | | 99a75523 |
| grpo_trainer.md | 55.4 kB | | b43f6347 |
| grpo_with_replay_buffer.html | 89.6 kB | | 84c012f9 |
| grpo_with_replay_buffer.md | 6.16 kB | | 2a88243b |
| gspo_token.html | 50.2 kB | | 269086e9 |
| gspo_token.md | 4.27 kB | | 9f5d68f5 |
| index.html | 29 kB | | 0db63930 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 03733453 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | b700e04e |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | 01884c07 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 137 kB | | 64e0750c |
| kto_trainer.md | 18.1 kB | | 8ea1e6c1 |
| liger_kernel_integration.html | 15 kB | | 2359ef74 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 836 kB | | eba32eb5 |
| llms.txt | 5 kB | | 5dcc054d |
| lora_without_regret.html | 45 kB | | d8534ebb |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | c9e3908a |
| merge_model_callback.md | 1.19 kB | | b1d9f281 |
| minillm_trainer.html | 179 kB | | b44c7e6c |
| minillm_trainer.md | 16.4 kB | | a0b76996 |
| nash_md_trainer.html | 124 kB | | df9b1ad4 |
| nash_md_trainer.md | 16.3 kB | | 08fdc8ad |
| nemo_gym.html | 58.5 kB | | c8f1bfe7 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.41 kB | | b2c3af22 |
| online_dpo_trainer.html | 179 kB | | c9921d58 |
| online_dpo_trainer.md | 23.1 kB | | ad851ebe |
| openenv.html | 114 kB | | 04620faf |
| openenv.md | 27.8 kB | | e7a45023 |
| orpo_trainer.html | 127 kB | | 4619ba9e |
| orpo_trainer.md | 17.7 kB | | 959309b1 |
| paper_index.html | 734 kB | | dbe6a097 |
| paper_index.md | 19.1 kB | | 7ae4e244 |
| papo_trainer.html | 111 kB | | d11faefe |
| papo_trainer.md | 8.82 kB | | 8f85bfbb |
| peft_integration.html | 131 kB | | 2dc8223a |
| peft_integration.md | 23.9 kB | | c9ee8110 |
| ppo_trainer.html | 278 kB | | 9f55b735 |
| ppo_trainer.md | 41.4 kB | | b64a34b6 |
| prm_trainer.html | 117 kB | | 01cbba56 |
| prm_trainer.md | 13.9 kB | | 8a4db9e3 |
| ptt_integration.html | 29.3 kB | | a464af96 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | fc0aa113 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | 5ca53c3f |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | c7850c0b |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
| reward_trainer.html | 175 kB | | 8d8245bc |
| reward_trainer.md | 21.5 kB | | 5d489029 |
|