| _app | | | 141 items |
| _toctree.yml | 3.29 kB | | 3ae9d845 |
| async_grpo_trainer.html | 108 kB | | 14c24ef4 |
| async_grpo_trainer.md | 12.3 kB | | 28f3efee |
| bco_trainer.html | 130 kB | | bcce5179 |
| bco_trainer.md | 14.1 kB | | 00d84dbf |
| bema_for_reference_model.html | 90 kB | | 7d767a71 |
| bema_for_reference_model.md | 7.18 kB | | fb8ba0a8 |
| callbacks.html | 95.8 kB | | 390d01c1 |
| callbacks.md | 7.88 kB | | cee1a2c1 |
| chat_template_utils.html | 45.5 kB | | 19c41f16 |
| chat_template_utils.md | 5.3 kB | | 92523a82 |
| clis.html | 53.4 kB | | 4c4c4e99 |
| clis.md | 12.8 kB | | 37963da2 |
| community_tutorials.html | 31 kB | | ce769499 |
| community_tutorials.md | 11 kB | | d1ade689 |
| cpo_trainer.html | 144 kB | | 3b1e49ca |
| cpo_trainer.md | 23 kB | | 15e1a114 |
| customization.html | 31 kB | | e7dd0a8d |
| customization.md | 4.08 kB | | edd5f7a7 |
| data_utils.html | 62.9 kB | | a65c9050 |
| data_utils.md | 6.32 kB | | ece90c71 |
| dataset_formats.html | 223 kB | | 1dab5506 |
| dataset_formats.md | 40.2 kB | | 598ca23c |
| deepspeed_integration.html | 15.8 kB | | 02d711ef |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | d865fe06 |
| distillation_trainer.md | 12.3 kB | | d4f00baf |
| distributing_training.html | 96.5 kB | | 02298925 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | d7e89045 |
| dpo_trainer.md | 30.8 kB | | 4d81864b |
| example_overview.html | 42.7 kB | | 68a615a5 |
| example_overview.md | 19.7 kB | | 699f7b37 |
| experimental_overview.html | 10.8 kB | | 1f9088de |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | a817d0a9 |
| gfpo.md | 5.24 kB | | 35514f44 |
| gkd_trainer.html | 119 kB | | 62a14f36 |
| gkd_trainer.md | 14.1 kB | | 1a41776e |
| gold_trainer.html | 166 kB | | a30e0413 |
| gold_trainer.md | 18.1 kB | | 4faf337b |
| grpo_trainer.html | 559 kB | | aae34f6a |
| grpo_trainer.md | 55.2 kB | | 52d2cab8 |
| grpo_with_replay_buffer.html | 89.6 kB | | afed4ea4 |
| grpo_with_replay_buffer.md | 6.16 kB | | 4885d36f |
| gspo_token.html | 50.2 kB | | 74b00acf |
| gspo_token.md | 4.27 kB | | c85a22e4 |
| index.html | 29 kB | | 2bf30dbb |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 59070ba0 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | e71f1759 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | 2a4082c6 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 137 kB | | 22fb1ee1 |
| kto_trainer.md | 18.1 kB | | b84818d6 |
| liger_kernel_integration.html | 15 kB | | b8a0fd1c |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 836 kB | | ff281066 |
| llms.txt | 5 kB | | 83f23f0d |
| lora_without_regret.html | 45 kB | | 318433d9 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 4867e256 |
| merge_model_callback.md | 1.19 kB | | 3e824923 |
| minillm_trainer.html | 179 kB | | 3ce2cfed |
| minillm_trainer.md | 16.4 kB | | 3ade08ad |
| nash_md_trainer.html | 124 kB | | acbb9645 |
| nash_md_trainer.md | 16.3 kB | | 4b2ed7a6 |
| nemo_gym.html | 58.5 kB | | 97bfd65b |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.41 kB | | eb4a7d7b |
| online_dpo_trainer.html | 179 kB | | 2cc236f5 |
| online_dpo_trainer.md | 23.1 kB | | 3136396b |
| openenv.html | 114 kB | | 5cb59446 |
| openenv.md | 27.8 kB | | 97ef2d46 |
| orpo_trainer.html | 127 kB | | edac1fad |
| orpo_trainer.md | 17.7 kB | | 6832158e |
| paper_index.html | 734 kB | | 00d42877 |
| paper_index.md | 19.1 kB | | ade8958c |
| papo_trainer.html | 111 kB | | aabf9f70 |
| papo_trainer.md | 8.82 kB | | 84092b35 |
| peft_integration.html | 131 kB | | 377649db |
| peft_integration.md | 23.9 kB | | e4f789ca |
| ppo_trainer.html | 278 kB | | b2e41029 |
| ppo_trainer.md | 41.4 kB | | 55cb905b |
| prm_trainer.html | 117 kB | | 72100e10 |
| prm_trainer.md | 13.9 kB | | e9c25494 |
| ptt_integration.html | 29.3 kB | | f9de6363 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | d2744742 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | 40fb4432 |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | a46993ab |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
| reward_trainer.html | 175 kB | | abac9bdc |
| reward_trainer.md | 21.5 kB | | 8828be1f |
|