| _app | | | 139 items |
| _toctree.yml | 3.2 kB | | f21731ac |
| async_grpo_trainer.html | 108 kB | | 53cdd24a |
| async_grpo_trainer.md | 12.3 kB | | b6b63dfa |
| bco_trainer.html | 130 kB | | 633ac762 |
| bco_trainer.md | 14.1 kB | | 72614ae9 |
| bema_for_reference_model.html | 90 kB | | 6d2e91e2 |
| bema_for_reference_model.md | 7.18 kB | | 4a16687f |
| callbacks.html | 95.8 kB | | 1a793a2e |
| callbacks.md | 7.88 kB | | 6e1f3dc7 |
| chat_template_utils.html | 45.5 kB | | 3a22b9d9 |
| chat_template_utils.md | 5.29 kB | | ad7da66f |
| clis.html | 53.4 kB | | 04cfd5cc |
| clis.md | 12.8 kB | | f07704c8 |
| community_tutorials.html | 31 kB | | 37d5f2da |
| community_tutorials.md | 11 kB | | 32489c90 |
| cpo_trainer.html | 144 kB | | ad3ba7c2 |
| cpo_trainer.md | 23 kB | | 104d409a |
| customization.html | 31 kB | | 6d86dae4 |
| customization.md | 4.08 kB | | 31b64878 |
| data_utils.html | 62.9 kB | | bf8e8530 |
| data_utils.md | 6.32 kB | | 776f5a2c |
| dataset_formats.html | 223 kB | | ab3c5339 |
| dataset_formats.md | 40.2 kB | | 2ca2a870 |
| deepspeed_integration.html | 15.8 kB | | be1185a3 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distributing_training.html | 96.5 kB | | d44747cb |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | 59e1716b |
| dpo_trainer.md | 30.7 kB | | 5a0f6ab3 |
| example_overview.html | 42.8 kB | | 2df22c1a |
| example_overview.md | 19.7 kB | | cee5eb88 |
| experimental_overview.html | 10.8 kB | | 639fa270 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | 782f17da |
| gfpo.md | 5.24 kB | | 0d662249 |
| gkd_trainer.html | 119 kB | | a8173d11 |
| gkd_trainer.md | 14.1 kB | | ab503bba |
| gold_trainer.html | 163 kB | | 2dbabeeb |
| gold_trainer.md | 17.5 kB | | b2ab458f |
| grpo_trainer.html | 559 kB | | 04ee215e |
| grpo_trainer.md | 55.2 kB | | 04639576 |
| grpo_with_replay_buffer.html | 89.6 kB | | 3955e60c |
| grpo_with_replay_buffer.md | 6.16 kB | | 6c8859eb |
| gspo_token.html | 50.2 kB | | 0cbadcb8 |
| gspo_token.md | 4.27 kB | | aa924050 |
| index.html | 29 kB | | 0cb8aba3 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 5e93bbdf |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 32eef671 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | 8f73897a |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 139 kB | | 5ac89adc |
| kto_trainer.md | 17.5 kB | | cd3aa8c0 |
| liger_kernel_integration.html | 15 kB | | 0d08165b |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 810 kB | | 4c82bf96 |
| llms.txt | 4.85 kB | | 3f87eb2a |
| lora_without_regret.html | 45 kB | | 149f4a04 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 1634220e |
| merge_model_callback.md | 1.19 kB | | 6f775ec2 |
| minillm_trainer.html | 179 kB | | 217af13a |
| minillm_trainer.md | 16.4 kB | | d80cc88f |
| nash_md_trainer.html | 125 kB | | b119aaa2 |
| nash_md_trainer.md | 16.3 kB | | a9cc9a7f |
| nemo_gym.html | 58.5 kB | | 4b250ba9 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.32 kB | | 95d62666 |
| online_dpo_trainer.html | 181 kB | | e8d02739 |
| online_dpo_trainer.md | 23.1 kB | | 34e56df6 |
| openenv.html | 114 kB | | be366f29 |
| openenv.md | 27.8 kB | | f70e382c |
| orpo_trainer.html | 127 kB | | 1a6cbea9 |
| orpo_trainer.md | 17.7 kB | | f5271300 |
| paper_index.html | 729 kB | | b94f207a |
| paper_index.md | 17.5 kB | | f87c7a69 |
| papo_trainer.html | 111 kB | | c5221862 |
| papo_trainer.md | 8.82 kB | | 5649948a |
| peft_integration.html | 131 kB | | 8e566046 |
| peft_integration.md | 23.9 kB | | 02170705 |
| ppo_trainer.html | 278 kB | | 701067cd |
| ppo_trainer.md | 41.4 kB | | e19fae77 |
| prm_trainer.html | 117 kB | | 23b2ebd7 |
| prm_trainer.md | 13.9 kB | | 20735d04 |
| ptt_integration.html | 29.3 kB | | a4bf5a7b |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 31cd1a90 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | 8c0ee7d6 |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | 708efaf6 |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
| reward_trainer.html | 175 kB | | ae5040d2 |
| reward_trainer.md | 21.5 kB | | 0bf24667 |
| rewards.html | 79.3 kB | | ce459602 |
| rewards.md | 6.78 kB | | 94356f36 |
|