| _app | | | 132 items |
| _toctree.yml | 3.15 kB | | 23c10302 |
| bco_trainer.html | 142 kB | | 12a58b2d |
| bco_trainer.md | 14.3 kB | | 8538a321 |
| bema_for_reference_model.html | 91.3 kB | | 4db3cc30 |
| bema_for_reference_model.md | 7.7 kB | | 238739f9 |
| callbacks.html | 101 kB | | 27e50485 |
| callbacks.md | 8.14 kB | | d117adfc |
| chat_template_utils.html | 69.1 kB | | a9b54a71 |
| chat_template_utils.md | 7.22 kB | | 2a4db928 |
| clis.html | 53.4 kB | | d6d0770c |
| clis.md | 12.8 kB | | 7c933da0 |
| community_tutorials.html | 31 kB | | 8983521b |
| community_tutorials.md | 10.9 kB | | b6a97a91 |
| cpo_trainer.html | 154 kB | | 062696c5 |
| cpo_trainer.md | 22.9 kB | | e2126aa5 |
| customization.html | 37.4 kB | | 9ca578b5 |
| customization.md | 4.9 kB | | 3b662bbe |
| data_utils.html | 177 kB | | 60b6d401 |
| data_utils.md | 18.9 kB | | 205e664d |
| dataset_formats.html | 219 kB | | cfe6b428 |
| dataset_formats.md | 41.2 kB | | a9c3cd5b |
| deepspeed_integration.html | 15.9 kB | | d41be36a |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distributing_training.html | 80.9 kB | | 6991b90b |
| distributing_training.md | 18.8 kB | | 3b39fd9e |
| dpo_trainer.html | 251 kB | | 89dcb896 |
| dpo_trainer.md | 35.4 kB | | 62b872db |
| example_overview.html | 35.6 kB | | 7b8cc208 |
| example_overview.md | 16.2 kB | | e67b88ec |
| experimental_overview.html | 10.8 kB | | 98def6fb |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 89.4 kB | | bd7292c0 |
| gfpo.md | 5.35 kB | | 431a505a |
| gkd_trainer.html | 123 kB | | 2844480e |
| gkd_trainer.md | 13.9 kB | | 61156980 |
| gold_trainer.html | 144 kB | | 7bb08625 |
| gold_trainer.md | 13.8 kB | | 1d43d1b3 |
| grpo_trainer.html | 536 kB | | 65a8d3a1 |
| grpo_trainer.md | 48.7 kB | | 383a61a8 |
| grpo_with_replay_buffer.html | 94.7 kB | | 41163385 |
| grpo_with_replay_buffer.md | 6.27 kB | | c4f01eeb |
| gspo_token.html | 50.6 kB | | 6b7aa116 |
| gspo_token.md | 4.38 kB | | 717784a3 |
| index.html | 28.6 kB | | e457ce53 |
| index.md | 3.68 kB | | a08ded5f |
| installation.html | 13.9 kB | | 4e70bf85 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 5918a7e0 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| judges.html | 119 kB | | 9df7c0f7 |
| judges.md | 15 kB | | 95ec679a |
| kernels_hub.html | 26.8 kB | | 52a92111 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 159 kB | | 3f20670d |
| kto_trainer.md | 20.7 kB | | ad54d7cd |
| liger_kernel_integration.html | 15 kB | | 42355734 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 818 kB | | bdbc2d6e |
| llms.txt | 4.76 kB | | 1ffeb1c8 |
| lora_without_regret.html | 45.1 kB | | 7946639a |
| lora_without_regret.md | 14.5 kB | | 38851bd7 |
| merge_model_callback.html | 17.8 kB | | c162edee |
| merge_model_callback.md | 1.19 kB | | a9685c18 |
| minillm_trainer.html | 184 kB | | d3e7ca0a |
| minillm_trainer.md | 16.5 kB | | 68eb686a |
| model_utils.html | 40.7 kB | | 94a8e8df |
| model_utils.md | 3.42 kB | | 137455da |
| nash_md_trainer.html | 134 kB | | 0d5cd0d8 |
| nash_md_trainer.md | 16.7 kB | | 79e415aa |
| objects.inv | 2.57 kB | | 8e4048d1 |
| online_dpo_trainer.html | 195 kB | | daf73d9c |
| online_dpo_trainer.md | 25.5 kB | | aa866922 |
| openenv.html | 86.6 kB | | 10a0e694 |
| openenv.md | 25.1 kB | | 31970e5b |
| orpo_trainer.html | 136 kB | | 5b895259 |
| orpo_trainer.md | 17.6 kB | | 193da695 |
| others.html | 29.7 kB | | d5a21131 |
| others.md | 2.18 kB | | 09c4ad7f |
| paper_index.html | 455 kB | | 401a2687 |
| paper_index.md | 28.1 kB | | 2c0e17de |
| papo_trainer.html | 116 kB | | 4363064b |
| papo_trainer.md | 8.83 kB | | 30fa701e |
| peft_integration.html | 131 kB | | 44094398 |
| peft_integration.md | 23.8 kB | | 575f6bb6 |
| ppo_trainer.html | 284 kB | | 8127b681 |
| ppo_trainer.md | 41.3 kB | | 175095d4 |
| prm_trainer.html | 123 kB | | 0fa89a26 |
| prm_trainer.md | 13.7 kB | | a3f393a5 |
| quickstart.html | 37.7 kB | | 1d2417df |
| quickstart.md | 3.36 kB | | 1a8bc789 |
| rapidfire_integration.html | 81.2 kB | | 506d0b46 |
| rapidfire_integration.md | 12.8 kB | | 33fdfe4a |
| reducing_memory_usage.html | 52.7 kB | | aa2c5b90 |
| reducing_memory_usage.md | 11.7 kB | | 12ee6a97 |
| reward_trainer.html | 199 kB | | ce364f09 |
| reward_trainer.md | 23.7 kB | | a685ce41 |
| rewards.html | 75.8 kB | | 10c5fbf9 |
| rewards.md | 6.31 kB | | 057dd4ab |
|