| _app | | | 191 items |
| _toctree.yml | 3.38 kB | | 9da8f3eb |
| async_grpo_trainer.html | 108 kB | | d3d2423c |
| async_grpo_trainer.md | 12.3 kB | | 7768dc7d |
| bco_trainer.html | 130 kB | | 19845dfb |
| bco_trainer.md | 14.2 kB | | e76d2d26 |
| bema_for_reference_model.html | 90 kB | | 580b1171 |
| bema_for_reference_model.md | 7.18 kB | | 3bb4eff7 |
| callbacks.html | 95.8 kB | | 224be41c |
| callbacks.md | 7.88 kB | | 940c7bb1 |
| chat_template_utils.html | 46.2 kB | | 7b69e4ca |
| chat_template_utils.md | 5.78 kB | | c0e8ecbf |
| chat_templates.html | 37.1 kB | | 615e15b2 |
| chat_templates.md | 7.04 kB | | def3e006 |
| clis.html | 53.4 kB | | c85e794d |
| clis.md | 12.8 kB | | 106344a0 |
| community_tutorials.html | 31 kB | | a18dec09 |
| community_tutorials.md | 11 kB | | 4081c042 |
| cpo_trainer.html | 145 kB | | 1451e8a6 |
| cpo_trainer.md | 23.2 kB | | 9952964a |
| customization.html | 31 kB | | 76f9ca0f |
| customization.md | 4.08 kB | | 1c58bd66 |
| data_utils.html | 62.7 kB | | abbc9208 |
| data_utils.md | 6.87 kB | | c9aa5b71 |
| dataset_formats.html | 223 kB | | bfe62a8a |
| dataset_formats.md | 43 kB | | 71321a5f |
| deepspeed_integration.html | 15.8 kB | | f88250f7 |
| deepspeed_integration.md | 1.52 kB | | e5b0fad5 |
| distillation_trainer.html | 161 kB | | d180fde4 |
| distillation_trainer.md | 12.3 kB | | 92c0db25 |
| distributing_training.html | 96.5 kB | | a888432e |
| distributing_training.md | 21 kB | | 75949925 |
| dpo_trainer.html | 233 kB | | 8e8cdac9 |
| dpo_trainer.md | 30.9 kB | | 8d20a397 |
| example_overview.html | 42.7 kB | | 6b501b68 |
| example_overview.md | 19.7 kB | | c012ffe6 |
| experimental_overview.html | 10.8 kB | | 0832deb2 |
| experimental_overview.md | 1.62 kB | | 45d90cc6 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 85 kB | | f4278bd2 |
| gfpo.md | 5.24 kB | | 06d2a146 |
| gkd_trainer.html | 119 kB | | b276bdc6 |
| gkd_trainer.md | 14.1 kB | | ab7a5725 |
| gold_trainer.html | 166 kB | | 438a448d |
| gold_trainer.md | 18.1 kB | | 73847ca6 |
| grpo_trainer.html | 561 kB | | 9184bd27 |
| grpo_trainer.md | 61.5 kB | | 06acdb72 |
| grpo_with_replay_buffer.html | 90.3 kB | | 4b6dbe53 |
| grpo_with_replay_buffer.md | 6.16 kB | | 25c096b7 |
| gspo_token.html | 50.2 kB | | 0e354158 |
| gspo_token.md | 4.27 kB | | 58c7aeef |
| index.html | 29 kB | | 60a6cb97 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 44016598 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | bcaa6e70 |
| jobs_training.md | 6.46 kB | | cb814663 |
| kernels_hub.html | 26.8 kB | | 06dd9ea0 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 134 kB | | 45416557 |
| kto_trainer.md | 18.2 kB | | ccb7f2ae |
| liger_kernel_integration.html | 15 kB | | 6ae74147 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 948 kB | | f54b2552 |
| llms.txt | 5.15 kB | | 9d385d26 |
| lora_without_regret.html | 45 kB | | 21e06b99 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | af8c5d35 |
| merge_model_callback.md | 1.19 kB | | 4f2d62fc |
| minillm_trainer.html | 180 kB | | 4a090441 |
| minillm_trainer.md | 16.4 kB | | 5f9f9585 |
| nash_md_trainer.html | 125 kB | | 108cb03f |
| nash_md_trainer.md | 16.6 kB | | a734e043 |
| nemo_gym.html | 58.5 kB | | bf660228 |
| nemo_gym.md | 10.3 kB | | 45caccd9 |
| objects.inv | 2.45 kB | | bddc9f86 |
| online_dpo_trainer.html | 180 kB | | bff4c213 |
| online_dpo_trainer.md | 23.3 kB | | 8bcba919 |
| openenv.html | 114 kB | | e13c533f |
| openenv.md | 27.8 kB | | ebffa5bf |
| orpo_trainer.html | 128 kB | | 4ba0c5f2 |
| orpo_trainer.md | 17.9 kB | | 3bbf8911 |
| paper_index.html | 743 kB | | c257042f |
| paper_index.md | 84.1 kB | | 54f3fde3 |
| papo_trainer.html | 112 kB | | c7308811 |
| papo_trainer.md | 8.82 kB | | 3b23c2da |
| peft_integration.html | 131 kB | | 721e3874 |
| peft_integration.md | 23.9 kB | | 7ab9e0fd |
| ppo_trainer.html | 279 kB | | 0daee02f |
| ppo_trainer.md | 41.5 kB | | 5c264719 |
| prm_trainer.html | 118 kB | | 65c2abc3 |
| prm_trainer.md | 14.2 kB | | 7448c59f |
| ptt_integration.html | 29.3 kB | | e5abf1b6 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 5d7347fd |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 95.4 kB | | a02d0e1d |
| rapidfire_integration.md | 17.8 kB | | b0dd6d2b |
| reducing_memory_usage.html | 57 kB | | b5ac8a77 |
| reducing_memory_usage.md | 13.7 kB | | 6e10323b |
|