| _app | | | 139 items |
| _toctree.yml | 3.22 kB | | ca36b740 |
| async_grpo_trainer.html | 108 kB | | 61a42d63 |
| async_grpo_trainer.md | 12.3 kB | | dbf53dff |
| bco_trainer.html | 131 kB | | 68587ff7 |
| bco_trainer.md | 14.4 kB | | a78b0abc |
| bema_for_reference_model.html | 90 kB | | 2220f28e |
| bema_for_reference_model.md | 7.18 kB | | 80ac8321 |
| callbacks.html | 95.8 kB | | 10dace3b |
| callbacks.md | 7.88 kB | | bb63ac0b |
| chat_template_utils.html | 43.9 kB | | 33ecef78 |
| chat_template_utils.md | 4.65 kB | | b508a0ba |
| clis.html | 53.4 kB | | 5257854a |
| clis.md | 12.8 kB | | 543f1b24 |
| community_tutorials.html | 31 kB | | 0e2cc1ee |
| community_tutorials.md | 11 kB | | 5bef7eb4 |
| cpo_trainer.html | 146 kB | | e5209a2d |
| cpo_trainer.md | 23.2 kB | | 80ea9be2 |
| customization.html | 31 kB | | c114f2d2 |
| customization.md | 4.08 kB | | 7d076b0d |
| data_utils.html | 62.9 kB | | 2d6ded1b |
| data_utils.md | 6.32 kB | | 9370e147 |
| dataset_formats.html | 223 kB | | d538865a |
| dataset_formats.md | 40.2 kB | | 498f6930 |
| deepspeed_integration.html | 15.8 kB | | 1d72e8de |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distributing_training.html | 96.5 kB | | ee732513 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 231 kB | | 1869aae6 |
| dpo_trainer.md | 30.6 kB | | 476184d4 |
| example_overview.html | 39.6 kB | | a49cd0ac |
| example_overview.md | 19.5 kB | | 8acb078c |
| experimental_overview.html | 10.8 kB | | e8d9f60e |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | c230a2e3 |
| gfpo.md | 5.24 kB | | 1420bcc2 |
| gkd_trainer.html | 119 kB | | 4b4ee4e9 |
| gkd_trainer.md | 14.1 kB | | 23fbadd6 |
| gold_trainer.html | 156 kB | | 12e38846 |
| gold_trainer.md | 16.8 kB | | 033004e1 |
| grpo_trainer.html | 554 kB | | e6300127 |
| grpo_trainer.md | 53.8 kB | | b99a803d |
| grpo_with_replay_buffer.html | 89.6 kB | | 3c46e43a |
| grpo_with_replay_buffer.md | 6.16 kB | | ce627c7d |
| gspo_token.html | 50.2 kB | | 25b63bcc |
| gspo_token.md | 4.27 kB | | 86d1fa8c |
| index.html | 28.8 kB | | efac6f7c |
| index.md | 3.68 kB | | 55bdb9e3 |
| installation.html | 13.9 kB | | cfc45553 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | e454f518 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| judges.html | 122 kB | | 0f7e4e74 |
| judges.md | 15.8 kB | | c4d6ce75 |
| kernels_hub.html | 26.8 kB | | e7eff5e6 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 138 kB | | 9102d060 |
| kto_trainer.md | 19.4 kB | | f8e7fd07 |
| liger_kernel_integration.html | 15 kB | | eb935586 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 809 kB | | 7c1203f6 |
| llms.txt | 4.91 kB | | 1c7f0ede |
| lora_without_regret.html | 45 kB | | ada81c5c |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 4a07807d |
| merge_model_callback.md | 1.19 kB | | c105196c |
| minillm_trainer.html | 179 kB | | 9ace3176 |
| minillm_trainer.md | 16.4 kB | | 333e0f4b |
| nash_md_trainer.html | 130 kB | | 43f7f6f7 |
| nash_md_trainer.md | 17.1 kB | | 3e6f73a5 |
| nemo_gym.html | 58.5 kB | | d25f5c4f |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.37 kB | | 91ef97cc |
| online_dpo_trainer.html | 195 kB | | c800ee42 |
| online_dpo_trainer.md | 26.3 kB | | 4206032e |
| openenv.html | 88.2 kB | | 5706ff2f |
| openenv.md | 25.4 kB | | 2908f003 |
| orpo_trainer.html | 129 kB | | 846b52ef |
| orpo_trainer.md | 17.9 kB | | 8690befd |
| paper_index.html | 717 kB | | 3babfc5f |
| paper_index.md | 13.8 kB | | 411cd046 |
| papo_trainer.html | 111 kB | | a7aaf171 |
| papo_trainer.md | 8.82 kB | | e484f25f |
| peft_integration.html | 131 kB | | 252ab554 |
| peft_integration.md | 23.9 kB | | 46828276 |
| ppo_trainer.html | 280 kB | | 53b60ba3 |
| ppo_trainer.md | 42 kB | | 677438d7 |
| prm_trainer.html | 117 kB | | db78ea38 |
| prm_trainer.md | 13.9 kB | | ff223d71 |
| ptt_integration.html | 29.3 kB | | 23a6e1cc |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | f0f19b90 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | 10c28530 |
| rapidfire_integration.md | 12.8 kB | | c14e6d99 |
| reducing_memory_usage.html | 52.4 kB | | 36453290 |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
| reward_trainer.html | 175 kB | | 7fb8b619 |
| reward_trainer.md | 21.5 kB | | 6b94db43 |
|