| _app | | | 137 items |
| _toctree.yml | 3.38 kB | | 9da8f3eb |
| async_grpo_trainer.html | 108 kB | | a2ed8d99 |
| async_grpo_trainer.md | 12.3 kB | | 20389e43 |
| bco_trainer.html | 130 kB | | 0e86e67c |
| bco_trainer.md | 14.2 kB | | d7962c65 |
| bema_for_reference_model.html | 90 kB | | 6987f5df |
| bema_for_reference_model.md | 7.18 kB | | 3cf71afa |
| callbacks.html | 95.8 kB | | fd38da0e |
| callbacks.md | 7.88 kB | | 3f8bb5a4 |
| chat_template_utils.html | 46.3 kB | | be3c83ed |
| chat_template_utils.md | 5.84 kB | | 170e1f16 |
| chat_templates.html | 44.7 kB | | 49b580a0 |
| chat_templates.md | 8.74 kB | | 76972798 |
| clis.html | 53.4 kB | | df6ed026 |
| clis.md | 12.8 kB | | 8ae1dd78 |
| community_tutorials.html | 31 kB | | 0fed5460 |
| community_tutorials.md | 11 kB | | ee089faa |
| cpo_trainer.html | 145 kB | | 074dbca3 |
| cpo_trainer.md | 23.2 kB | | ced8000a |
| customization.html | 31 kB | | 18e308bf |
| customization.md | 4.08 kB | | e1c0a4f4 |
| data_utils.html | 62.7 kB | | 4e0ea397 |
| data_utils.md | 6.87 kB | | 5f17dc1c |
| dataset_formats.html | 223 kB | | 3905282e |
| dataset_formats.md | 43 kB | | ce5401ac |
| deepspeed_integration.html | 15.8 kB | | 0fd84f28 |
| deepspeed_integration.md | 1.52 kB | | e5b0fad5 |
| distillation_trainer.html | 161 kB | | 518123fd |
| distillation_trainer.md | 12.3 kB | | c232a764 |
| distributing_training.html | 96.5 kB | | 57d54860 |
| distributing_training.md | 21 kB | | 75949925 |
| dpo_trainer.html | 233 kB | | bba7fcd7 |
| dpo_trainer.md | 31.1 kB | | afda227b |
| example_overview.html | 42.8 kB | | c04eb04b |
| example_overview.md | 19.7 kB | | f7077147 |
| experimental_overview.html | 10.8 kB | | 08d2735f |
| experimental_overview.md | 1.62 kB | | 45d90cc6 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 85 kB | | 4b74001b |
| gfpo.md | 5.24 kB | | 7cbac442 |
| gkd_trainer.html | 119 kB | | 884a15ab |
| gkd_trainer.md | 14.1 kB | | c7e5d5e6 |
| gold_trainer.html | 166 kB | | 366e7261 |
| gold_trainer.md | 18.1 kB | | 5878fba6 |
| grpo_trainer.html | 561 kB | | 129473fd |
| grpo_trainer.md | 61.5 kB | | edc06937 |
| grpo_with_replay_buffer.html | 90.3 kB | | 8398f208 |
| grpo_with_replay_buffer.md | 6.16 kB | | 16cd9acd |
| gspo_token.html | 50.2 kB | | fb4dc071 |
| gspo_token.md | 4.27 kB | | 7590fc38 |
| index.html | 29 kB | | 535684c1 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | f7605ff1 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 4568bfb3 |
| jobs_training.md | 6.46 kB | | cb814663 |
| kernels_hub.html | 26.8 kB | | 54110645 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 134 kB | | 55075437 |
| kto_trainer.md | 18.2 kB | | 377f625e |
| liger_kernel_integration.html | 15 kB | | c805de8e |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 954 kB | | 48c23aca |
| llms.txt | 5.15 kB | | a2a604a8 |
| lora_without_regret.html | 45 kB | | 0e939fd8 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 1d32f6fa |
| merge_model_callback.md | 1.19 kB | | 12c4e439 |
| minillm_trainer.html | 180 kB | | adbd58ec |
| minillm_trainer.md | 16.4 kB | | ae36339d |
| nash_md_trainer.html | 125 kB | | 619a6007 |
| nash_md_trainer.md | 16.6 kB | | f554ad31 |
| nemo_gym.html | 58.5 kB | | a526b625 |
| nemo_gym.md | 10.3 kB | | 45caccd9 |
| objects.inv | 2.45 kB | | 86bad22e |
| online_dpo_trainer.html | 180 kB | | 23e054ed |
| online_dpo_trainer.md | 23.3 kB | | 76fd3aab |
| openenv.html | 114 kB | | a9a5f9b0 |
| openenv.md | 27.8 kB | | 04be8fab |
| orpo_trainer.html | 128 kB | | 1c557acf |
| orpo_trainer.md | 17.9 kB | | 70013a7e |
| paper_index.html | 770 kB | | de4be826 |
| paper_index.md | 87.8 kB | | 38767ef4 |
| papo_trainer.html | 112 kB | | 06846117 |
| papo_trainer.md | 8.82 kB | | f9b48e61 |
| peft_integration.html | 131 kB | | 4584ce3c |
| peft_integration.md | 23.9 kB | | dc427dbb |
| ppo_trainer.html | 279 kB | | 4f50c2d6 |
| ppo_trainer.md | 41.5 kB | | 5e8ce91f |
| prm_trainer.html | 118 kB | | b2b081f5 |
| prm_trainer.md | 14.2 kB | | 0744b821 |
| ptt_integration.html | 29.3 kB | | 9c073d85 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 1e0305c3 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 95.4 kB | | a7dbd455 |
| rapidfire_integration.md | 17.8 kB | | b0dd6d2b |
| reducing_memory_usage.html | 57.1 kB | | c80866c8 |
| reducing_memory_usage.md | 13.7 kB | | 04e9376b |
|