| _app | | | 1,993 items |
| internal | | | 11 items |
| main_classes | | | 21 items |
| model_doc | | | 350 items |
| quantization | | | 22 items |
| tasks | | | 31 items |
| _redirects.yml | 128 Bytes | | 03cac062 |
| _toctree.yml | 32 kB | | 6c0ec213 |
| accelerate.html | 27.9 kB | | 6ae4fe0e |
| add_new_model.html | 136 kB | | d124ae05 |
| add_new_pipeline.html | 46.3 kB | | 3e55a740 |
| agents.html | 3.11 kB | | 64442080 |
| attention.html | 24.2 kB | | e36883de |
| attention_interface.html | 24.7 kB | | 1e48dd8d |
| backbones.html | 25 kB | | 93242fbd |
| cache_explanation.html | 18.7 kB | | 4253c690 |
| chat_extras.html | 45.8 kB | | d7b21788 |
| chat_templating.html | 50.3 kB | | 13c9baba |
| chat_templating_multimodal.html | 36.7 kB | | b2e55566 |
| chat_templating_writing.html | 61.7 kB | | a2568079 |
| community.html | 43.4 kB | | cd7f9ef2 |
| contributing.html | 72.8 kB | | 1c943cf0 |
| conversations.html | 30.7 kB | | c9c121fa |
| custom_models.html | 46.5 kB | | 0c7c10b5 |
| debugging.html | 65.4 kB | | 4a3e3de4 |
| deepspeed.html | 134 kB | | 6cdac04e |
| executorch.html | 10.1 kB | | 9321e1a8 |
| fast_tokenizers.html | 72 kB | | 9c1b6887 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| feature_extractors.html | 39 kB | | 30f59c01 |
| fsdp.html | 34.6 kB | | 4c61a95b |
| generation_features.html | 17.9 kB | | 21af3c9f |
| generation_strategies.html | 60.8 kB | | 179e1303 |
| gguf.html | 9.68 kB | | 4ae9a7e8 |
| glossary.html | 152 kB | | f8e53e08 |
| gpu_selection.html | 19.3 kB | | f3b4e33f |
| how_to_hack_models.html | 28.8 kB | | 36659aeb |
| hpo_train.html | 19 kB | | f3a753cb |
| image_processors.html | 40.8 kB | | be9c441a |
| index.html | 9.59 kB | | 9326a4a2 |
| installation.html | 42.1 kB | | 1a6bd7ca |
| kv_cache.html | 71.1 kB | | 2588150b |
| llm_optims.html | 46 kB | | f1a2f085 |
| llm_tutorial.html | 56.6 kB | | 517ed231 |
| llm_tutorial_optimization.html | 246 kB | | da9198ca |
| model_memory_anatomy.html | 39.8 kB | | 700aefaa |
| model_sharing.html | 36.7 kB | | ca997a31 |
| model_summary.html | 43.9 kB | | 9b0585b4 |
| models.html | 58 kB | | b502b67d |
| modular_transformers.html | 107 kB | | 573a2ffe |
| notebooks.html | 70.3 kB | | 8040da89 |
| objects.inv | 43.4 kB | | 6018fe33 |
| optimizers.html | 30.5 kB | | b7c77753 |
| pad_truncation.html | 10.7 kB | | 8a8a85d0 |
| peft.html | 29.2 kB | | 8cf549e7 |
| perf_hardware.html | 14.8 kB | | 5f2c66ea |
| perf_infer_cpu.html | 22.5 kB | | 3c263d0b |
| perf_infer_gpu_multi.html | 12.3 kB | | c8a036ea |
| perf_infer_gpu_one.html | 47.5 kB | | 18c3279f |
| perf_torch_compile.html | 16 kB | | 0a08c3c4 |
| perf_train_cpu.html | 14.3 kB | | 355b40c5 |
| perf_train_cpu_many.html | 40.4 kB | | 352410c5 |
| perf_train_gpu_many.html | 29.1 kB | | 3265509c |
| perf_train_gpu_one.html | 49.5 kB | | 85907c3a |
| perf_train_special.html | 7.33 kB | | 78ce9bc5 |
| perf_train_tpu_tf.html | 68.2 kB | | 5ce94484 |
| perplexity.html | 39.3 kB | | 0bbde152 |
| philosophy.html | 11.7 kB | | 54661a94 |
| pipeline_gradio.html | 9.99 kB | | 4dfdea7e |
| pipeline_tutorial.html | 61.7 kB | | 8bbd0f5c |
| pipeline_webserver.html | 30.4 kB | | 1729a80e |
| pr_checks.html | 44.1 kB | | 3676b1b7 |
| processors.html | 22 kB | | b16f9518 |
| quicktour.html | 54.7 kB | | 1bc732a0 |
| run_scripts.html | 34.7 kB | | bb285111 |
| serialization.html | 22.7 kB | | 6b1edbe5 |
| serving.html | 15.2 kB | | 53409aa7 |
| task_summary.html | 83.7 kB | | b23a4658 |
| tasks_explained.html | 60.4 kB | | 2f01a241 |
| testing.html | 250 kB | | b0483ea9 |
| tf_xla.html | 26.2 kB | | d6933a1f |
| tflite.html | 13.8 kB | | d079c53a |
| tokenizer_summary.html | 66 kB | | 4500f960 |
| tools.html | 3.11 kB | | dd79d03b |
| torchscript.html | 28.4 kB | | d1f3eca3 |
| trainer.html | 70 kB | | 7b38821f |
| training.html | 36.8 kB | | 9d5b0387 |
| troubleshooting.html | 47.2 kB | | 5d81a892 |
