| _app | | | 141 items |
| _toctree.yml | 3.29 kB | | 3ae9d845 |
| async_grpo_trainer.html | 108 kB | | a662ec10 |
| async_grpo_trainer.md | 12.3 kB | | f6445309 |
| bco_trainer.html | 130 kB | | 9c712c41 |
| bco_trainer.md | 14.1 kB | | 4593143b |
| bema_for_reference_model.html | 90 kB | | 8c140986 |
| bema_for_reference_model.md | 7.18 kB | | d97b3bdf |
| callbacks.html | 95.8 kB | | 1516288a |
| callbacks.md | 7.88 kB | | 596178ac |
| chat_template_utils.html | 45.7 kB | | 55150fec |
| chat_template_utils.md | 5.34 kB | | d9fa2b33 |
| clis.html | 53.4 kB | | 15574cb3 |
| clis.md | 12.8 kB | | 0991e85d |
| community_tutorials.html | 31 kB | | edd6dff2 |
| community_tutorials.md | 11 kB | | c529bf02 |
| cpo_trainer.html | 144 kB | | 99a9afe4 |
| cpo_trainer.md | 23 kB | | de9a71a0 |
| customization.html | 31 kB | | c3284f69 |
| customization.md | 4.08 kB | | f7daba25 |
| data_utils.html | 62.9 kB | | b9b60d27 |
| data_utils.md | 6.32 kB | | e4eb43d2 |
| dataset_formats.html | 223 kB | | 2bbccd57 |
| dataset_formats.md | 40.2 kB | | f30f34a9 |
| deepspeed_integration.html | 15.8 kB | | acf4e5dd |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | 5b741bcd |
| distillation_trainer.md | 12.3 kB | | 4f80649e |
| distributing_training.html | 96.5 kB | | 04968721 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | 5bc4b458 |
| dpo_trainer.md | 30.8 kB | | f366fb19 |
| example_overview.html | 42.8 kB | | b42c06d2 |
| example_overview.md | 19.7 kB | | c93baaa6 |
| experimental_overview.html | 10.8 kB | | 38deb468 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | 2709d72f |
| gfpo.md | 5.24 kB | | 56dce188 |
| gkd_trainer.html | 119 kB | | 7a16ba71 |
| gkd_trainer.md | 14.1 kB | | 8c35485e |
| gold_trainer.html | 166 kB | | b80bb8a8 |
| gold_trainer.md | 18.1 kB | | 0840f82a |
| grpo_trainer.html | 560 kB | | 4bd51123 |
| grpo_trainer.md | 55.4 kB | | 0880abdc |
| grpo_with_replay_buffer.html | 89.6 kB | | b4792345 |
| grpo_with_replay_buffer.md | 6.16 kB | | cc123648 |
| gspo_token.html | 50.2 kB | | 7617dcf8 |
| gspo_token.md | 4.27 kB | | 716a69c4 |
| index.html | 29 kB | | 0c760569 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 87f0fb35 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | b8257691 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | 446ccf78 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 137 kB | | d2a1e463 |
| kto_trainer.md | 18.1 kB | | bf34b62d |
| liger_kernel_integration.html | 15 kB | | 99d814e7 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 836 kB | | 3a16a653 |
| llms.txt | 5 kB | | 21de3ec7 |
| lora_without_regret.html | 45 kB | | 0893223a |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 5e04e7a5 |
| merge_model_callback.md | 1.19 kB | | 9b1c6922 |
| minillm_trainer.html | 179 kB | | 5358bcae |
| minillm_trainer.md | 16.4 kB | | 976bf38e |
| nash_md_trainer.html | 124 kB | | c495d55c |
| nash_md_trainer.md | 16.3 kB | | f2db3ad4 |
| nemo_gym.html | 58.5 kB | | cc583d29 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.41 kB | | 4235c1f2 |
| online_dpo_trainer.html | 179 kB | | 3b34df21 |
| online_dpo_trainer.md | 23.1 kB | | b2828aab |
| openenv.html | 114 kB | | 144ece14 |
| openenv.md | 27.8 kB | | 67beea16 |
| orpo_trainer.html | 127 kB | | dabc9215 |
| orpo_trainer.md | 17.7 kB | | b53c20f5 |
| paper_index.html | 734 kB | | 3719b32e |
| paper_index.md | 19.1 kB | | 22f1a531 |
| papo_trainer.html | 111 kB | | cbd6ff06 |
| papo_trainer.md | 8.82 kB | | d5d80cf6 |
| peft_integration.html | 131 kB | | de2b57f0 |
| peft_integration.md | 23.9 kB | | 4aa54a97 |
| ppo_trainer.html | 278 kB | | 1a7e1725 |
| ppo_trainer.md | 41.4 kB | | a127ac19 |
| prm_trainer.html | 117 kB | | 5cd54d33 |
| prm_trainer.md | 13.9 kB | | 083ba3e4 |
| ptt_integration.html | 29.3 kB | | 78a46518 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | c3097995 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | bdfe1b7a |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | 984da6c4 |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
| reward_trainer.html | 175 kB | | 4f68eec7 |
| reward_trainer.md | 21.5 kB | | 6402ae27 |
|