| _app | | | 141 items |
| _toctree.yml | 3.29 kB | | 3ae9d845 |
| async_grpo_trainer.html | 108 kB | | a0f04373 |
| async_grpo_trainer.md | 12.3 kB | | d47904c9 |
| bco_trainer.html | 130 kB | | 4d6ef302 |
| bco_trainer.md | 14.1 kB | | f8cf1225 |
| bema_for_reference_model.html | 90 kB | | b9dc52de |
| bema_for_reference_model.md | 7.18 kB | | 2498b805 |
| callbacks.html | 95.8 kB | | 6ac44c9f |
| callbacks.md | 7.88 kB | | ea1c68cd |
| chat_template_utils.html | 45.5 kB | | 928c1697 |
| chat_template_utils.md | 5.3 kB | | 11828397 |
| clis.html | 53.4 kB | | 2dccce90 |
| clis.md | 12.8 kB | | 480e1142 |
| community_tutorials.html | 31 kB | | 4dcdd8e2 |
| community_tutorials.md | 11 kB | | 03d5de2f |
| cpo_trainer.html | 144 kB | | fd072d7d |
| cpo_trainer.md | 23 kB | | f6e46e79 |
| customization.html | 31 kB | | ac6d5127 |
| customization.md | 4.08 kB | | 2231973e |
| data_utils.html | 62.9 kB | | e15fffc7 |
| data_utils.md | 6.32 kB | | b635cc72 |
| dataset_formats.html | 223 kB | | c4784971 |
| dataset_formats.md | 40.2 kB | | 2e36f0c6 |
| deepspeed_integration.html | 15.8 kB | | 5b5bf02d |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | 94fb2fbf |
| distillation_trainer.md | 12.3 kB | | 4689fe11 |
| distributing_training.html | 96.5 kB | | 0a87845a |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | 70b6f757 |
| dpo_trainer.md | 30.8 kB | | 91d210d3 |
| example_overview.html | 42.7 kB | | 4fac482d |
| example_overview.md | 19.7 kB | | 661ba472 |
| experimental_overview.html | 10.8 kB | | dc13e921 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | 15f9d0c8 |
| gfpo.md | 5.24 kB | | 6d69c453 |
| gkd_trainer.html | 119 kB | | abc42980 |
| gkd_trainer.md | 14.1 kB | | 51f64c12 |
| gold_trainer.html | 166 kB | | a1e8e578 |
| gold_trainer.md | 18.1 kB | | 9d859759 |
| grpo_trainer.html | 559 kB | | 25ba6f95 |
| grpo_trainer.md | 55.2 kB | | 46abc5e2 |
| grpo_with_replay_buffer.html | 89.6 kB | | 71e22974 |
| grpo_with_replay_buffer.md | 6.16 kB | | a56968b6 |
| gspo_token.html | 50.2 kB | | 1b409987 |
| gspo_token.md | 4.27 kB | | 8d753b87 |
| index.html | 29 kB | | 479494d4 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 720c7a2b |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 7ee6c354 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | 601f60ff |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 137 kB | | f42d93d6 |
| kto_trainer.md | 18.1 kB | | 7b094edb |
| liger_kernel_integration.html | 15 kB | | a4e536cc |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 836 kB | | 18403cbf |
| llms.txt | 5 kB | | 42e07e2b |
| lora_without_regret.html | 45 kB | | fc4f3647 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 4b22e20a |
| merge_model_callback.md | 1.19 kB | | 96700414 |
| minillm_trainer.html | 179 kB | | bfe08fa3 |
| minillm_trainer.md | 16.4 kB | | 7cd37a00 |
| nash_md_trainer.html | 124 kB | | c9570cff |
| nash_md_trainer.md | 16.3 kB | | c0c4b1a2 |
| nemo_gym.html | 58.5 kB | | cfac1b87 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.41 kB | | f18d895f |
| online_dpo_trainer.html | 179 kB | | 6382b141 |
| online_dpo_trainer.md | 23.1 kB | | 8a647f91 |
| openenv.html | 114 kB | | 2c1ab81a |
| openenv.md | 27.8 kB | | af86e3af |
| orpo_trainer.html | 127 kB | | e5b3c87f |
| orpo_trainer.md | 17.7 kB | | 5b4e5294 |
| paper_index.html | 734 kB | | b920850f |
| paper_index.md | 19.1 kB | | de1602e6 |
| papo_trainer.html | 111 kB | | af5b948e |
| papo_trainer.md | 8.82 kB | | 737261c9 |
| peft_integration.html | 131 kB | | b5d70dd1 |
| peft_integration.md | 23.9 kB | | 5d2c1f2a |
| ppo_trainer.html | 278 kB | | 910cc924 |
| ppo_trainer.md | 41.4 kB | | 2efcc1b9 |
| prm_trainer.html | 117 kB | | adb873c0 |
| prm_trainer.md | 13.9 kB | | 1f17d04e |
| ptt_integration.html | 29.3 kB | | dea627c1 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 9ef786e6 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | c863daeb |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | 0ebb6879 |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
| reward_trainer.html | 175 kB | | b63b2c4c |
| reward_trainer.md | 21.5 kB | | 4697aec7 |
|