| _app | | | 164 items |
| _toctree.yml | 3.38 kB | | 9da8f3eb |
| async_grpo_trainer.html | 108 kB | | 150427a4 |
| async_grpo_trainer.md | 12.3 kB | | e8186a1c |
| bco_trainer.html | 130 kB | | ec2087e7 |
| bco_trainer.md | 14.1 kB | | 0efa0795 |
| bema_for_reference_model.html | 90 kB | | 56f360f0 |
| bema_for_reference_model.md | 7.18 kB | | b5c53e1f |
| callbacks.html | 95.8 kB | | d5b015fa |
| callbacks.md | 7.88 kB | | 7ac2fcbd |
| chat_template_utils.html | 45.8 kB | | 09db0261 |
| chat_template_utils.md | 5.48 kB | | b19644b0 |
| chat_templates.html | 28.3 kB | | cb0acbe0 |
| chat_templates.md | 5.13 kB | | 0a092290 |
| clis.html | 53.4 kB | | 58f3ff7b |
| clis.md | 12.8 kB | | da42c0df |
| community_tutorials.html | 31 kB | | 43578b2f |
| community_tutorials.md | 10.9 kB | | 14b75e7a |
| cpo_trainer.html | 144 kB | | 7ea40f82 |
| cpo_trainer.md | 23 kB | | 1f145de2 |
| customization.html | 30.9 kB | | d08a2b83 |
| customization.md | 4.04 kB | | 5fd984db |
| data_utils.html | 62.7 kB | | ad685559 |
| data_utils.md | 6.87 kB | | 525fda30 |
| dataset_formats.html | 223 kB | | 087cd1c3 |
| dataset_formats.md | 40.1 kB | | 882d75b0 |
| deepspeed_integration.html | 15.8 kB | | 40c6336a |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | 0e8f333f |
| distillation_trainer.md | 12.3 kB | | eb09d49e |
| distributing_training.html | 96.5 kB | | e55d76ed |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | b2a29000 |
| dpo_trainer.md | 30.7 kB | | 42ec77c7 |
| example_overview.html | 42.7 kB | | e5c3c85a |
| example_overview.md | 19.6 kB | | 4ce3f577 |
| experimental_overview.html | 10.8 kB | | 1b9d54d2 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | 617baef9 |
| gfpo.md | 5.24 kB | | eda3a7c5 |
| gkd_trainer.html | 119 kB | | d8df7b5a |
| gkd_trainer.md | 14.1 kB | | 0bcdc0de |
| gold_trainer.html | 166 kB | | 960626ad |
| gold_trainer.md | 18.1 kB | | 0eabe644 |
| grpo_trainer.html | 560 kB | | 1454903f |
| grpo_trainer.md | 55.8 kB | | f3122c10 |
| grpo_with_replay_buffer.html | 89.6 kB | | 5487a1e3 |
| grpo_with_replay_buffer.md | 6.16 kB | | bd33ec35 |
| gspo_token.html | 50.2 kB | | a6dae7ff |
| gspo_token.md | 4.27 kB | | 3bd1e69e |
| index.html | 29 kB | | d107b4fc |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | dd54b1f4 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | cb4330ac |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | 2aad724d |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 137 kB | | ec4d1559 |
| kto_trainer.md | 18.4 kB | | 17e475dd |
| liger_kernel_integration.html | 15 kB | | 7143b1f5 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 866 kB | | 24c4be62 |
| llms.txt | 5.15 kB | | bfce2a6d |
| lora_without_regret.html | 45 kB | | 153db23a |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | d261a2a3 |
| merge_model_callback.md | 1.19 kB | | a0bb62f4 |
| minillm_trainer.html | 179 kB | | 0ba25578 |
| minillm_trainer.md | 16.4 kB | | 664d3d95 |
| nash_md_trainer.html | 124 kB | | ce0f5d7b |
| nash_md_trainer.md | 16.3 kB | | aa0bb476 |
| nemo_gym.html | 58.5 kB | | 257451da |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.44 kB | | 7a1fc66c |
| online_dpo_trainer.html | 179 kB | | 184246f3 |
| online_dpo_trainer.md | 23.1 kB | | 7e163dc5 |
| openenv.html | 114 kB | | 51d55a9a |
| openenv.md | 27.8 kB | | c82a8a0a |
| orpo_trainer.html | 127 kB | | df62aed5 |
| orpo_trainer.md | 17.7 kB | | de2ca1cf |
| paper_index.html | 742 kB | | 10650f84 |
| paper_index.md | 19.1 kB | | b5119ed8 |
| papo_trainer.html | 111 kB | | 1d3eba62 |
| papo_trainer.md | 8.82 kB | | 9cdd198a |
| peft_integration.html | 131 kB | | 5286d070 |
| peft_integration.md | 23.9 kB | | 23df7dd3 |
| ppo_trainer.html | 278 kB | | f0077915 |
| ppo_trainer.md | 41.4 kB | | aba47f37 |
| prm_trainer.html | 117 kB | | 3a86b130 |
| prm_trainer.md | 13.9 kB | | 32005f46 |
| ptt_integration.html | 29.3 kB | | 7a6b58e8 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | c1819c18 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 95.4 kB | | d31b3d20 |
| rapidfire_integration.md | 17.7 kB | | 08fed5af |
| reducing_memory_usage.html | 52.4 kB | | e904da03 |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
|