| _app | | | 251 items |
| _toctree.yml | 3.29 kB | | 3ae9d845 |
| async_grpo_trainer.html | 108 kB | | 2fd046c0 |
| async_grpo_trainer.md | 12.3 kB | | 5aa82d12 |
| bco_trainer.html | 130 kB | | f745d418 |
| bco_trainer.md | 14.1 kB | | 017d4ea5 |
| bema_for_reference_model.html | 90 kB | | 55818848 |
| bema_for_reference_model.md | 7.18 kB | | b6ddfd5c |
| callbacks.html | 95.8 kB | | a89512b0 |
| callbacks.md | 7.88 kB | | e7adb8d4 |
| chat_template_utils.html | 45.5 kB | | 6058b3c0 |
| chat_template_utils.md | 5.29 kB | | 984cd3b7 |
| clis.html | 53.4 kB | | 1208a737 |
| clis.md | 12.8 kB | | 57edbc75 |
| community_tutorials.html | 31 kB | | 872e24d2 |
| community_tutorials.md | 11 kB | | 01b11699 |
| cpo_trainer.html | 144 kB | | 5575172d |
| cpo_trainer.md | 23 kB | | 14b78dee |
| customization.html | 31 kB | | 4a8b2eb3 |
| customization.md | 4.08 kB | | 7cf85555 |
| data_utils.html | 62.9 kB | | 50e546af |
| data_utils.md | 6.32 kB | | 37fe290f |
| dataset_formats.html | 223 kB | | ee75980d |
| dataset_formats.md | 40.2 kB | | a85bda85 |
| deepspeed_integration.html | 15.8 kB | | 705f1adb |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 155 kB | | 6d38c205 |
| distillation_trainer.md | 11.1 kB | | 2bbdad32 |
| distributing_training.html | 96.5 kB | | 921c64d8 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | 05954c94 |
| dpo_trainer.md | 30.7 kB | | 3acf670f |
| example_overview.html | 42.8 kB | | 1d495184 |
| example_overview.md | 19.7 kB | | 09c653ae |
| experimental_overview.html | 10.8 kB | | eb1602e6 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | aa2e3928 |
| gfpo.md | 5.24 kB | | dd9516af |
| gkd_trainer.html | 119 kB | | f8546502 |
| gkd_trainer.md | 14.1 kB | | 2b4a4fa8 |
| gold_trainer.html | 163 kB | | 9eb158a4 |
| gold_trainer.md | 17.5 kB | | ce25aae9 |
| grpo_trainer.html | 559 kB | | 9538a7fb |
| grpo_trainer.md | 55.2 kB | | 69a5ebdd |
| grpo_with_replay_buffer.html | 89.6 kB | | d2cf1772 |
| grpo_with_replay_buffer.md | 6.16 kB | | c8822d84 |
| gspo_token.html | 50.2 kB | | 3cadd93d |
| gspo_token.md | 4.27 kB | | 84011ef4 |
| index.html | 29 kB | | 4d8798a3 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | d828bae0 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 5da2959c |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | cd6dc091 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 139 kB | | 4c1fc3dc |
| kto_trainer.md | 17.5 kB | | 588eafe0 |
| liger_kernel_integration.html | 15 kB | | 0e117992 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 831 kB | | 6df01e5c |
| llms.txt | 5 kB | | cd31f9fa |
| lora_without_regret.html | 45 kB | | 3a8da621 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | c6fc9469 |
| merge_model_callback.md | 1.19 kB | | 0428c99d |
| minillm_trainer.html | 179 kB | | 6408cf17 |
| minillm_trainer.md | 16.4 kB | | 4ab9f106 |
| nash_md_trainer.html | 125 kB | | 5f8ae11e |
| nash_md_trainer.md | 16.3 kB | | 4ac2a4d3 |
| nemo_gym.html | 58.5 kB | | 381daae6 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.41 kB | | 37f13bd3 |
| online_dpo_trainer.html | 181 kB | | a5f9abf3 |
| online_dpo_trainer.md | 23.1 kB | | 7d555509 |
| openenv.html | 114 kB | | 605f8c98 |
| openenv.md | 27.8 kB | | 42bde53d |
| orpo_trainer.html | 127 kB | | 239802d8 |
| orpo_trainer.md | 17.7 kB | | 5b4f5e46 |
| paper_index.html | 734 kB | | 8a880cd4 |
| paper_index.md | 19.1 kB | | 1d0bf17b |
| papo_trainer.html | 111 kB | | a69bc9e4 |
| papo_trainer.md | 8.82 kB | | a23dad72 |
| peft_integration.html | 131 kB | | 97c2c07c |
| peft_integration.md | 23.9 kB | | 621c336b |
| ppo_trainer.html | 278 kB | | 53aad289 |
| ppo_trainer.md | 41.4 kB | | 7943bb49 |
| prm_trainer.html | 117 kB | | 1416cc6f |
| prm_trainer.md | 13.9 kB | | 89890f0d |
| ptt_integration.html | 29.3 kB | | 3822da63 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 3ff6dcd2 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | 78c7e259 |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | 383a0234 |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
| reward_trainer.html | 175 kB | | 56c13ab4 |
| reward_trainer.md | 21.5 kB | | 5c7f474f |
|