| _app | | | 135 items |
| _toctree.yml | 3.29 kB | | 3ae9d845 |
| async_grpo_trainer.html | 108 kB | | 36192b33 |
| async_grpo_trainer.md | 12.3 kB | | e7c0a515 |
| bco_trainer.html | 130 kB | | 89adf5c1 |
| bco_trainer.md | 14.1 kB | | af906bf3 |
| bema_for_reference_model.html | 90 kB | | 886d2aeb |
| bema_for_reference_model.md | 7.18 kB | | b9c069c4 |
| callbacks.html | 95.8 kB | | f2f4f511 |
| callbacks.md | 7.88 kB | | 61728c40 |
| chat_template_utils.html | 45.7 kB | | 65a1dc0f |
| chat_template_utils.md | 5.34 kB | | 4f42ca12 |
| clis.html | 53.4 kB | | 6f4f3351 |
| clis.md | 12.8 kB | | 860c0350 |
| community_tutorials.html | 31 kB | | a9c5beb7 |
| community_tutorials.md | 11 kB | | 3fcf64b4 |
| cpo_trainer.html | 144 kB | | c386176d |
| cpo_trainer.md | 23 kB | | 0e386277 |
| customization.html | 31 kB | | 43f569e4 |
| customization.md | 4.08 kB | | f5294f2e |
| data_utils.html | 62.9 kB | | ec4fa135 |
| data_utils.md | 6.32 kB | | 105e24ae |
| dataset_formats.html | 223 kB | | 71485f6b |
| dataset_formats.md | 40.2 kB | | 979362b7 |
| deepspeed_integration.html | 15.8 kB | | 58c7ca34 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | ad8cb832 |
| distillation_trainer.md | 12.3 kB | | 0445a653 |
| distributing_training.html | 96.5 kB | | e3404791 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | c66c01a9 |
| dpo_trainer.md | 30.8 kB | | f56e32a6 |
| example_overview.html | 42.8 kB | | 5292a2e8 |
| example_overview.md | 19.7 kB | | 4e52310e |
| experimental_overview.html | 10.8 kB | | 63e9a807 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | dff8cd71 |
| gfpo.md | 5.24 kB | | a4dc3af6 |
| gkd_trainer.html | 119 kB | | 3b5a7159 |
| gkd_trainer.md | 14.1 kB | | 7e6b1270 |
| gold_trainer.html | 166 kB | | deceb523 |
| gold_trainer.md | 18.1 kB | | 1045e6ab |
| grpo_trainer.html | 560 kB | | bee78bb4 |
| grpo_trainer.md | 55.4 kB | | 79f8ff48 |
| grpo_with_replay_buffer.html | 89.6 kB | | 0171186f |
| grpo_with_replay_buffer.md | 6.16 kB | | 63070534 |
| gspo_token.html | 50.2 kB | | 4086d993 |
| gspo_token.md | 4.27 kB | | e2026809 |
| index.html | 29 kB | | f034b8b0 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 95ec8624 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 12d37c78 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | 331e49a7 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 137 kB | | dbeb38bd |
| kto_trainer.md | 18.1 kB | | 9f488311 |
| liger_kernel_integration.html | 15 kB | | 51a2d014 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 836 kB | | ad06d029 |
| llms.txt | 5 kB | | 9855936a |
| lora_without_regret.html | 45 kB | | 028d651c |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 73a4c2da |
| merge_model_callback.md | 1.19 kB | | 41400965 |
| minillm_trainer.html | 179 kB | | 783727bf |
| minillm_trainer.md | 16.4 kB | | 7ca37fde |
| nash_md_trainer.html | 124 kB | | b19fbe1e |
| nash_md_trainer.md | 16.3 kB | | e82ae9a3 |
| nemo_gym.html | 58.5 kB | | a40802c7 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.41 kB | | 0ddf2bd9 |
| online_dpo_trainer.html | 179 kB | | c0ffa168 |
| online_dpo_trainer.md | 23.1 kB | | 4b180862 |
| openenv.html | 114 kB | | eb35cc45 |
| openenv.md | 27.8 kB | | fd31ed7c |
| orpo_trainer.html | 127 kB | | 88eb738d |
| orpo_trainer.md | 17.7 kB | | b1cf2a75 |
| paper_index.html | 734 kB | | 5d3d6fa8 |
| paper_index.md | 19.1 kB | | 248d615d |
| papo_trainer.html | 111 kB | | e97ee6cb |
| papo_trainer.md | 8.82 kB | | 5f3cf432 |
| peft_integration.html | 131 kB | | 72629be4 |
| peft_integration.md | 23.9 kB | | 0d803bcd |
| ppo_trainer.html | 278 kB | | 0276d6fa |
| ppo_trainer.md | 41.4 kB | | 6194c9ff |
| prm_trainer.html | 117 kB | | e18a6dbc |
| prm_trainer.md | 13.9 kB | | da04ecb7 |
| ptt_integration.html | 29.3 kB | | e2a88fca |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | dff52f0b |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | ab4b2404 |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | 5915da99 |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
| reward_trainer.html | 175 kB | | 1687b728 |
| reward_trainer.md | 21.5 kB | | 0c7bda37 |
|