| _app | | | 162 items |
| _toctree.yml | 3.29 kB | | 3ae9d845 |
| async_grpo_trainer.html | 108 kB | | c48ce2e1 |
| async_grpo_trainer.md | 12.3 kB | | 5ac9904d |
| bco_trainer.html | 130 kB | | 55debbfb |
| bco_trainer.md | 14.1 kB | | 6600f20f |
| bema_for_reference_model.html | 90 kB | | 912cb617 |
| bema_for_reference_model.md | 7.18 kB | | 5f084c20 |
| callbacks.html | 95.8 kB | | 0cd936b4 |
| callbacks.md | 7.88 kB | | 3f9b62ab |
| chat_template_utils.html | 45.5 kB | | cc9e43e3 |
| chat_template_utils.md | 5.3 kB | | 4b1da336 |
| clis.html | 53.4 kB | | a28b2db2 |
| clis.md | 12.8 kB | | 6ce28a03 |
| community_tutorials.html | 31 kB | | e9daabc6 |
| community_tutorials.md | 11 kB | | 330aa4bc |
| cpo_trainer.html | 144 kB | | 256effec |
| cpo_trainer.md | 23 kB | | f5b70d47 |
| customization.html | 31 kB | | 700daeef |
| customization.md | 4.08 kB | | 9035c733 |
| data_utils.html | 62.9 kB | | f306d079 |
| data_utils.md | 6.32 kB | | dea4007f |
| dataset_formats.html | 223 kB | | 8d6056ca |
| dataset_formats.md | 40.2 kB | | f81ba708 |
| deepspeed_integration.html | 15.8 kB | | 132869d4 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | 67efd373 |
| distillation_trainer.md | 12.3 kB | | e90c2402 |
| distributing_training.html | 96.5 kB | | cf9df39e |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | 4d23912c |
| dpo_trainer.md | 30.8 kB | | a509c6c0 |
| example_overview.html | 42.8 kB | | 103cbdc9 |
| example_overview.md | 19.7 kB | | 21939c62 |
| experimental_overview.html | 10.8 kB | | 97cfc326 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | 9bfae153 |
| gfpo.md | 5.24 kB | | a135cc57 |
| gkd_trainer.html | 119 kB | | e5c92179 |
| gkd_trainer.md | 14.1 kB | | 06425ada |
| gold_trainer.html | 166 kB | | 5fdec124 |
| gold_trainer.md | 18.1 kB | | 609b3f87 |
| grpo_trainer.html | 559 kB | | 290eb332 |
| grpo_trainer.md | 55.2 kB | | b05b3b3a |
| grpo_with_replay_buffer.html | 89.6 kB | | 0557b11e |
| grpo_with_replay_buffer.md | 6.16 kB | | af2acabd |
| gspo_token.html | 50.2 kB | | 63f0cc5a |
| gspo_token.md | 4.27 kB | | 15fa75a7 |
| index.html | 29 kB | | 75577a14 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 7bdd1a04 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 0e6ef5c4 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | b78a8dbe |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 137 kB | | 421aa403 |
| kto_trainer.md | 18.1 kB | | 11614542 |
| liger_kernel_integration.html | 15 kB | | 9790b7ed |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 836 kB | | 99145d4f |
| llms.txt | 5 kB | | 4af321ee |
| lora_without_regret.html | 45 kB | | d475c904 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 121d0956 |
| merge_model_callback.md | 1.19 kB | | 3017096a |
| minillm_trainer.html | 179 kB | | 1dfd8e47 |
| minillm_trainer.md | 16.4 kB | | fac2aaf9 |
| nash_md_trainer.html | 124 kB | | 811f60ba |
| nash_md_trainer.md | 16.3 kB | | d730174b |
| nemo_gym.html | 58.5 kB | | 82e3779e |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.41 kB | | 0e226ba8 |
| online_dpo_trainer.html | 179 kB | | b560de30 |
| online_dpo_trainer.md | 23.1 kB | | 326a76a9 |
| openenv.html | 114 kB | | 561b0060 |
| openenv.md | 27.8 kB | | 6cbd5848 |
| orpo_trainer.html | 127 kB | | 2037c5ce |
| orpo_trainer.md | 17.7 kB | | 7064defa |
| paper_index.html | 734 kB | | 6c45577a |
| paper_index.md | 19.1 kB | | e79d7f87 |
| papo_trainer.html | 111 kB | | d23b350f |
| papo_trainer.md | 8.82 kB | | 380fa279 |
| peft_integration.html | 131 kB | | 32d5529a |
| peft_integration.md | 23.9 kB | | 937b053c |
| ppo_trainer.html | 278 kB | | aa47da40 |
| ppo_trainer.md | 41.4 kB | | 4c8afbd6 |
| prm_trainer.html | 117 kB | | e1cb3f34 |
| prm_trainer.md | 13.9 kB | | a9faf747 |
| ptt_integration.html | 29.3 kB | | 9beadcd2 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 179334c5 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | 03c2d9bb |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | e3c9cf59 |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
| reward_trainer.html | 175 kB | | 0e5f4b3c |
| reward_trainer.md | 21.5 kB | | 23290f9f |
|