| _app | | | 220 items |
| _toctree.yml | 3.29 kB | | 3ae9d845 |
| async_grpo_trainer.html | 108 kB | | 39174763 |
| async_grpo_trainer.md | 12.3 kB | | b25037c2 |
| bco_trainer.html | 130 kB | | 2228f1ef |
| bco_trainer.md | 14.1 kB | | 1216b8c2 |
| bema_for_reference_model.html | 90 kB | | 5190eb3d |
| bema_for_reference_model.md | 7.18 kB | | ee57e809 |
| callbacks.html | 95.8 kB | | baec090f |
| callbacks.md | 7.88 kB | | 8dd9c63c |
| chat_template_utils.html | 45.5 kB | | 2e57ae0c |
| chat_template_utils.md | 5.3 kB | | a4ef9271 |
| clis.html | 53.4 kB | | a4d23912 |
| clis.md | 12.8 kB | | dbc61324 |
| community_tutorials.html | 31 kB | | a100a6a3 |
| community_tutorials.md | 11 kB | | a5af62a1 |
| cpo_trainer.html | 144 kB | | 3ac665ba |
| cpo_trainer.md | 23 kB | | 837c1545 |
| customization.html | 31 kB | | 4d35c558 |
| customization.md | 4.08 kB | | 864e9667 |
| data_utils.html | 62.9 kB | | 7f2889df |
| data_utils.md | 6.32 kB | | 2ff5bc1b |
| dataset_formats.html | 223 kB | | 09774a81 |
| dataset_formats.md | 40.2 kB | | 43195109 |
| deepspeed_integration.html | 15.8 kB | | 0035c7ff |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | 2ab3e623 |
| distillation_trainer.md | 12.3 kB | | 4cc52e05 |
| distributing_training.html | 96.5 kB | | 561678b3 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | 57e0192b |
| dpo_trainer.md | 30.8 kB | | af5ace76 |
| example_overview.html | 42.8 kB | | 01498b6c |
| example_overview.md | 19.7 kB | | 51e27b92 |
| experimental_overview.html | 10.8 kB | | d31776da |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | 3b444739 |
| gfpo.md | 5.24 kB | | 1c8197a4 |
| gkd_trainer.html | 119 kB | | 13c5349c |
| gkd_trainer.md | 14.1 kB | | 87936bfc |
| gold_trainer.html | 166 kB | | 8974d709 |
| gold_trainer.md | 18.1 kB | | 94bb2e38 |
| grpo_trainer.html | 560 kB | | 1bc911bb |
| grpo_trainer.md | 55.4 kB | | 06ce0b4a |
| grpo_with_replay_buffer.html | 89.6 kB | | f63a64d8 |
| grpo_with_replay_buffer.md | 6.16 kB | | e3605571 |
| gspo_token.html | 50.2 kB | | 8a6c61aa |
| gspo_token.md | 4.27 kB | | 11334b8c |
| index.html | 29 kB | | 75902d14 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | c4659261 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | c7a6ae77 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| judges.html | 122 kB | | 486c00c4 |
| judges.md | 15.8 kB | | 914b18cb |
| kernels_hub.html | 26.8 kB | | e1b20107 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 137 kB | | f85b0f2b |
| kto_trainer.md | 18.1 kB | | f6ed241b |
| liger_kernel_integration.html | 15 kB | | 1f3ce4a7 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 836 kB | | 66fe2a52 |
| llms.txt | 5 kB | | 5cb77fa4 |
| lora_without_regret.html | 45 kB | | 7cf50bae |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | f6757552 |
| merge_model_callback.md | 1.19 kB | | f0c7d7de |
| minillm_trainer.html | 179 kB | | 1439e1f4 |
| minillm_trainer.md | 16.4 kB | | 9f1b3e9e |
| nash_md_trainer.html | 124 kB | | 3a46725d |
| nash_md_trainer.md | 16.3 kB | | cc79552a |
| nemo_gym.html | 58.5 kB | | 2a69d516 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.41 kB | | d004926a |
| online_dpo_trainer.html | 179 kB | | 8aae1b47 |
| online_dpo_trainer.md | 23.1 kB | | 4b220739 |
| openenv.html | 114 kB | | 1da7f7e3 |
| openenv.md | 27.8 kB | | f85c7704 |
| orpo_trainer.html | 127 kB | | 615cef1c |
| orpo_trainer.md | 17.7 kB | | 6e935a09 |
| paper_index.html | 734 kB | | 54f78abb |
| paper_index.md | 19.1 kB | | 988707bc |
| papo_trainer.html | 111 kB | | b1eadc92 |
| papo_trainer.md | 8.82 kB | | 1d4d9ed2 |
| peft_integration.html | 131 kB | | 7f849130 |
| peft_integration.md | 23.9 kB | | d3518250 |
| ppo_trainer.html | 278 kB | | 88a9b7e5 |
| ppo_trainer.md | 41.4 kB | | ed6243ad |
| prm_trainer.html | 117 kB | | 8932bdd2 |
| prm_trainer.md | 13.9 kB | | 196133c4 |
| ptt_integration.html | 29.3 kB | | e3cdf7a9 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 001c5948 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | 00ad42ac |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | 5f2b594f |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
|