| _app | | | 233 items |
| _toctree.yml | 3.35 kB | | ac839051 |
| async_grpo_trainer.html | 108 kB | | bef70ca2 |
| async_grpo_trainer.md | 12.3 kB | | 9671a56b |
| bco_trainer.html | 130 kB | | 0786e55f |
| bco_trainer.md | 14.1 kB | | 570787e8 |
| bema_for_reference_model.html | 90 kB | | 977547fc |
| bema_for_reference_model.md | 7.18 kB | | 86fc067a |
| callbacks.html | 95.8 kB | | 429d1d38 |
| callbacks.md | 7.88 kB | | 07c91cd7 |
| chat_template_utils.html | 45.8 kB | | 143b8399 |
| chat_template_utils.md | 5.48 kB | | a5c1ad36 |
| chat_templates.html | 28.3 kB | | 8ff12313 |
| chat_templates.md | 5.13 kB | | 038f0493 |
| clis.html | 53.4 kB | | e79feae0 |
| clis.md | 12.8 kB | | 91eef83e |
| community_tutorials.html | 31 kB | | e77461db |
| community_tutorials.md | 11 kB | | 7ab10468 |
| cpo_trainer.html | 144 kB | | 977a169c |
| cpo_trainer.md | 23 kB | | a135cfd0 |
| customization.html | 31 kB | | 3d98e502 |
| customization.md | 4.08 kB | | 50595cca |
| data_utils.html | 62.7 kB | | ed9e3efc |
| data_utils.md | 6.87 kB | | d511ea8d |
| dataset_formats.html | 223 kB | | 48aa08c1 |
| dataset_formats.md | 40.2 kB | | ccc1820a |
| deepspeed_integration.html | 15.8 kB | | fbb98609 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | 272eb3cf |
| distillation_trainer.md | 12.3 kB | | d9ab9fee |
| distributing_training.html | 96.5 kB | | 04d31320 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | 11c734f8 |
| dpo_trainer.md | 30.8 kB | | f63d5eec |
| example_overview.html | 42.7 kB | | 70e05b21 |
| example_overview.md | 19.7 kB | | d84a2b2f |
| experimental_overview.html | 10.8 kB | | 264d3ee9 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | 018b9aa2 |
| gfpo.md | 5.24 kB | | 7987fc14 |
| gkd_trainer.html | 119 kB | | e9a29d18 |
| gkd_trainer.md | 14.1 kB | | 445b3783 |
| gold_trainer.html | 166 kB | | 3d90b63c |
| gold_trainer.md | 18.1 kB | | fb41b166 |
| grpo_trainer.html | 560 kB | | 8b2d9312 |
| grpo_trainer.md | 55.8 kB | | cf046ddc |
| grpo_with_replay_buffer.html | 89.6 kB | | e9f5bdf8 |
| grpo_with_replay_buffer.md | 6.16 kB | | 8e1007fc |
| gspo_token.html | 50.2 kB | | 2216c0a0 |
| gspo_token.md | 4.27 kB | | b6b9d994 |
| index.html | 29 kB | | d8a6489a |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 8f6eb7aa |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 26dc840d |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | f219b97f |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 137 kB | | 07f4626f |
| kto_trainer.md | 18.4 kB | | 2004e88a |
| liger_kernel_integration.html | 15 kB | | 8aba9149 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 843 kB | | 520a794b |
| llms.txt | 5.08 kB | | 805fb11a |
| lora_without_regret.html | 45 kB | | 0ec2ace3 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 0ea67a9e |
| merge_model_callback.md | 1.19 kB | | 19c269b3 |
| minillm_trainer.html | 179 kB | | bb04612b |
| minillm_trainer.md | 16.4 kB | | 86fc5a42 |
| nash_md_trainer.html | 124 kB | | dca24b6f |
| nash_md_trainer.md | 16.3 kB | | 99dc7c1a |
| nemo_gym.html | 58.5 kB | | bec2a7e2 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.41 kB | | 53461fae |
| online_dpo_trainer.html | 179 kB | | a2fd0602 |
| online_dpo_trainer.md | 23.1 kB | | 57c48d52 |
| openenv.html | 114 kB | | 805d0f86 |
| openenv.md | 27.8 kB | | 03a46e0f |
| orpo_trainer.html | 127 kB | | 8943c52f |
| orpo_trainer.md | 17.7 kB | | a91ceca0 |
| paper_index.html | 734 kB | | 4d8811c8 |
| paper_index.md | 19.1 kB | | 6a66ad87 |
| papo_trainer.html | 111 kB | | f208997b |
| papo_trainer.md | 8.82 kB | | f7a78541 |
| peft_integration.html | 131 kB | | d63d48f5 |
| peft_integration.md | 23.9 kB | | 1c5b26d0 |
| ppo_trainer.html | 278 kB | | 1c373ce5 |
| ppo_trainer.md | 41.4 kB | | 843db4eb |
| prm_trainer.html | 117 kB | | afafd125 |
| prm_trainer.md | 13.9 kB | | f126dc18 |
| ptt_integration.html | 29.3 kB | | 4adf4bb9 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | e59c84c0 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | 409109e9 |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | d1f5ec03 |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
|