| _app | | | 206 items |
| _toctree.yml | 3.35 kB | | ac839051 |
| async_grpo_trainer.html | 108 kB | | bf8225d5 |
| async_grpo_trainer.md | 12.3 kB | | 019e57e6 |
| bco_trainer.html | 130 kB | | 6c2f3455 |
| bco_trainer.md | 14.1 kB | | c9a752d8 |
| bema_for_reference_model.html | 90 kB | | a572dce0 |
| bema_for_reference_model.md | 7.18 kB | | cf709490 |
| callbacks.html | 95.8 kB | | d6219485 |
| callbacks.md | 7.88 kB | | 5c5f9288 |
| chat_template_utils.html | 45.8 kB | | 568eb546 |
| chat_template_utils.md | 5.48 kB | | c386c724 |
| chat_templates.html | 28.3 kB | | 3b74f20e |
| chat_templates.md | 5.13 kB | | 2570f157 |
| clis.html | 53.4 kB | | b2fbe833 |
| clis.md | 12.8 kB | | fe3d13c4 |
| community_tutorials.html | 31 kB | | cbfd4125 |
| community_tutorials.md | 11 kB | | 1711c622 |
| cpo_trainer.html | 144 kB | | 9bde833e |
| cpo_trainer.md | 23 kB | | 1c3c21f2 |
| customization.html | 31 kB | | 52b30cf8 |
| customization.md | 4.08 kB | | 90872525 |
| data_utils.html | 62.7 kB | | 7eeea9f7 |
| data_utils.md | 6.87 kB | | c252fda4 |
| dataset_formats.html | 223 kB | | b527a561 |
| dataset_formats.md | 40.2 kB | | 340d7376 |
| deepspeed_integration.html | 15.8 kB | | da1ace21 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | e5aa48bc |
| distillation_trainer.md | 12.3 kB | | d862f8b3 |
| distributing_training.html | 96.5 kB | | 633cad4c |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | a6070f3f |
| dpo_trainer.md | 30.8 kB | | a1e013b8 |
| example_overview.html | 42.8 kB | | e8f12b8d |
| example_overview.md | 19.7 kB | | 36bda590 |
| experimental_overview.html | 10.8 kB | | 746432dc |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | 21b4b9cd |
| gfpo.md | 5.24 kB | | 3e3e6200 |
| gkd_trainer.html | 119 kB | | 9994c4a7 |
| gkd_trainer.md | 14.1 kB | | 0c2d0252 |
| gold_trainer.html | 166 kB | | a3719469 |
| gold_trainer.md | 18.1 kB | | 27b46517 |
| grpo_trainer.html | 560 kB | | c5d1ab8d |
| grpo_trainer.md | 55.8 kB | | 6570c4ef |
| grpo_with_replay_buffer.html | 89.6 kB | | db09ab1e |
| grpo_with_replay_buffer.md | 6.16 kB | | c1aab7f9 |
| gspo_token.html | 50.2 kB | | 993e694d |
| gspo_token.md | 4.27 kB | | e251b097 |
| index.html | 29 kB | | 0b30b433 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | ed9096fa |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 75f71c0f |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | 5120ebf9 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 137 kB | | 6cb0805d |
| kto_trainer.md | 18.4 kB | | 7fa4383f |
| liger_kernel_integration.html | 15 kB | | b9313b87 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 843 kB | | 62d9389f |
| llms.txt | 5.08 kB | | 72746902 |
| lora_without_regret.html | 45 kB | | 532bd710 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | e80b64fa |
| merge_model_callback.md | 1.19 kB | | 285a41fd |
| minillm_trainer.html | 179 kB | | b99ae6dc |
| minillm_trainer.md | 16.4 kB | | 4a86ac5e |
| nash_md_trainer.html | 124 kB | | eb07f917 |
| nash_md_trainer.md | 16.3 kB | | d6392ad1 |
| nemo_gym.html | 58.5 kB | | 8d2fd82f |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.41 kB | | 3a3c61b3 |
| online_dpo_trainer.html | 179 kB | | ff8cffae |
| online_dpo_trainer.md | 23.1 kB | | 95f40324 |
| openenv.html | 114 kB | | c8538305 |
| openenv.md | 27.8 kB | | caf029e7 |
| orpo_trainer.html | 127 kB | | 445e44d2 |
| orpo_trainer.md | 17.7 kB | | f1f570b1 |
| paper_index.html | 734 kB | | 0d82efbd |
| paper_index.md | 19.1 kB | | 7c87632c |
| papo_trainer.html | 111 kB | | e8ed6f67 |
| papo_trainer.md | 8.82 kB | | 1c072183 |
| peft_integration.html | 131 kB | | cb0f4722 |
| peft_integration.md | 23.9 kB | | 7c990a09 |
| ppo_trainer.html | 278 kB | | 651e0aef |
| ppo_trainer.md | 41.4 kB | | 55311613 |
| prm_trainer.html | 117 kB | | 3792b0ff |
| prm_trainer.md | 13.9 kB | | 253e28c0 |
| ptt_integration.html | 29.3 kB | | 96fbd908 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 3950e011 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | 0a94eb4c |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | 66b17ff1 |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
|