| _app | | | 169 items |
| _toctree.yml | 3.29 kB | | 3ae9d845 |
| async_grpo_trainer.html | 108 kB | | d7474c1c |
| async_grpo_trainer.md | 12.3 kB | | 43c0ebfd |
| bco_trainer.html | 130 kB | | ccc3bf5c |
| bco_trainer.md | 14.1 kB | | 323c6d8b |
| bema_for_reference_model.html | 90 kB | | 032ea89e |
| bema_for_reference_model.md | 7.18 kB | | 93f558c7 |
| callbacks.html | 95.8 kB | | 1eef2654 |
| callbacks.md | 7.88 kB | | 2eaccc40 |
| chat_template_utils.html | 45.5 kB | | 7fc84ad4 |
| chat_template_utils.md | 5.3 kB | | 5e4e26b1 |
| clis.html | 53.4 kB | | e1028255 |
| clis.md | 12.8 kB | | 95a41d9f |
| community_tutorials.html | 31 kB | | 3f88f0e8 |
| community_tutorials.md | 11 kB | | 7523ad91 |
| cpo_trainer.html | 144 kB | | 2e029ec5 |
| cpo_trainer.md | 23 kB | | 56090f7b |
| customization.html | 31 kB | | 2a44c362 |
| customization.md | 4.08 kB | | 1969ceb1 |
| data_utils.html | 62.9 kB | | a5bc9b44 |
| data_utils.md | 6.32 kB | | efbbec9a |
| dataset_formats.html | 223 kB | | 12545271 |
| dataset_formats.md | 40.2 kB | | b01231ea |
| deepspeed_integration.html | 15.8 kB | | 738fc9e4 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | d6051fe3 |
| distillation_trainer.md | 12.3 kB | | 0e1fe61b |
| distributing_training.html | 96.5 kB | | 17440714 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | 5bfa786b |
| dpo_trainer.md | 30.8 kB | | 7ef0fc62 |
| example_overview.html | 42.8 kB | | 41f64f0c |
| example_overview.md | 19.7 kB | | 7a98b326 |
| experimental_overview.html | 10.8 kB | | 72446bd4 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | 83bd9c10 |
| gfpo.md | 5.24 kB | | 54572f1d |
| gkd_trainer.html | 119 kB | | ab62aa37 |
| gkd_trainer.md | 14.1 kB | | 8e857dbc |
| gold_trainer.html | 166 kB | | 036394e9 |
| gold_trainer.md | 18.1 kB | | a6a3e59c |
| grpo_trainer.html | 560 kB | | 740206ad |
| grpo_trainer.md | 55.4 kB | | 6d9bb199 |
| grpo_with_replay_buffer.html | 89.6 kB | | 69c3b50f |
| grpo_with_replay_buffer.md | 6.16 kB | | dccf170e |
| gspo_token.html | 50.2 kB | | 46972d12 |
| gspo_token.md | 4.27 kB | | 5fdc143f |
| index.html | 29 kB | | 9250bb3b |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 523c155d |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | b6e916ee |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | ec5fdb95 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 137 kB | | df1bed25 |
| kto_trainer.md | 18.1 kB | | fe9cce48 |
| liger_kernel_integration.html | 15 kB | | 5c97617e |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 836 kB | | cbfd1b30 |
| llms.txt | 5 kB | | 3a656111 |
| lora_without_regret.html | 45 kB | | 8603e63f |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 80cc10b3 |
| merge_model_callback.md | 1.19 kB | | c21448be |
| minillm_trainer.html | 179 kB | | bf1016b5 |
| minillm_trainer.md | 16.4 kB | | 7c94f669 |
| nash_md_trainer.html | 124 kB | | 5d9d2bc5 |
| nash_md_trainer.md | 16.3 kB | | 72922f1f |
| nemo_gym.html | 58.5 kB | | 75f78de1 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.41 kB | | e9f2a2a4 |
| online_dpo_trainer.html | 179 kB | | abb2dc9d |
| online_dpo_trainer.md | 23.1 kB | | a30fc5e0 |
| openenv.html | 114 kB | | 1c803d32 |
| openenv.md | 27.8 kB | | 64e1c6fc |
| orpo_trainer.html | 127 kB | | 796d0793 |
| orpo_trainer.md | 17.7 kB | | ac0c075c |
| paper_index.html | 734 kB | | e700457f |
| paper_index.md | 19.1 kB | | 9419d0e3 |
| papo_trainer.html | 111 kB | | 07fcbe65 |
| papo_trainer.md | 8.82 kB | | f1885044 |
| peft_integration.html | 131 kB | | d2041d7f |
| peft_integration.md | 23.9 kB | | 2f7f01b4 |
| ppo_trainer.html | 278 kB | | a8f24054 |
| ppo_trainer.md | 41.4 kB | | 287fdf75 |
| prm_trainer.html | 117 kB | | 3afd6336 |
| prm_trainer.md | 13.9 kB | | 086405b0 |
| ptt_integration.html | 29.3 kB | | 354b83cc |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 34ae6fbc |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | f479911a |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | 7fb64aef |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
| reward_trainer.html | 175 kB | | b2462216 |
| reward_trainer.md | 21.5 kB | | e1d94ba2 |
|