| _app | | | 527 items |
| internal | | | 10 items |
| main_classes | | | 22 items |
| model_doc | | | 343 items |
| quantization | | | 19 items |
| tasks | | | 30 items |
| _redirects.yml | 128 Bytes | | 03cac062 |
| _toctree.yml | 31.3 kB | | 5be24f22 |
| accelerate.html | 27.7 kB | | 8da7e8f8 |
| add_new_model.html | 136 kB | | 59141cd5 |
| add_new_pipeline.html | 46.2 kB | | 6cc4e17a |
| agents.html | 50.4 kB | | d499cb73 |
| attention.html | 24 kB | | 3c27045b |
| attention_interface.html | 24.6 kB | | d99a829d |
| backbones.html | 24.9 kB | | fc2f8817 |
| cache_explanation.html | 18.6 kB | | ef425cb7 |
| chat_extras.html | 45.7 kB | | 4ae65c08 |
| chat_templating.html | 50.2 kB | | a28616ed |
| chat_templating_multimodal.html | 36.8 kB | | 9ce6c861 |
| chat_templating_writing.html | 61.6 kB | | ede620ae |
| community.html | 43.2 kB | | 8cb02c55 |
| contributing.html | 72.7 kB | | 07aba702 |
| conversations.html | 30.6 kB | | b18298a4 |
| custom_models.html | 46.4 kB | | 58d8dc3b |
| debugging.html | 65.3 kB | | 0a142af7 |
| deepspeed.html | 134 kB | | 2d3192e2 |
| executorch.html | 10 kB | | 079ea821 |
| fast_tokenizers.html | 71.9 kB | | 84180ff7 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| feature_extractors.html | 38.9 kB | | a38f3476 |
| fsdp.html | 34.5 kB | | f91b5e40 |
| generation_features.html | 17.8 kB | | bec6d58e |
| generation_strategies.html | 60.6 kB | | 2b5fb8f9 |
| gguf.html | 9.57 kB | | c13f5bcf |
| glossary.html | 152 kB | | 85e3c664 |
| gpu_selection.html | 19.2 kB | | e9d7dc33 |
| how_to_hack_models.html | 28.7 kB | | 2a99d9c9 |
| hpo_train.html | 18.9 kB | | 4490e970 |
| image_processors.html | 40.7 kB | | dfe78b2b |
| index.html | 9.48 kB | | 8e012f8c |
| installation.html | 42 kB | | 21a90d01 |
| kv_cache.html | 71 kB | | 077045be |
| llm_optims.html | 45.8 kB | | fc8e8221 |
| llm_tutorial.html | 56.5 kB | | e0d960de |
| llm_tutorial_optimization.html | 246 kB | | d21c181d |
| model_memory_anatomy.html | 39.6 kB | | bb8a0d91 |
| model_sharing.html | 36.6 kB | | a3488e4d |
| model_summary.html | 43.8 kB | | 204ab1e6 |
| models.html | 57.9 kB | | 0ea845c2 |
| modular_transformers.html | 107 kB | | 443305bf |
| notebooks.html | 70.2 kB | | 0038d3ea |
| objects.inv | 42.9 kB | | 3b700e8e |
| optimizers.html | 30.4 kB | | 10bc6c01 |
| pad_truncation.html | 10.5 kB | | c20faa2e |
| peft.html | 29.1 kB | | 729281cd |
| perf_hardware.html | 14.6 kB | | 8b440ae6 |
| perf_infer_cpu.html | 22.4 kB | | 1cd10897 |
| perf_infer_gpu_multi.html | 12.2 kB | | 8bc67161 |
| perf_infer_gpu_one.html | 47.4 kB | | 834975dc |
| perf_torch_compile.html | 15.9 kB | | 745a63af |
| perf_train_cpu.html | 14.2 kB | | c9c6ca9e |
| perf_train_cpu_many.html | 40.3 kB | | ec337e66 |
| perf_train_gpu_many.html | 29 kB | | 0a21ccb4 |
| perf_train_gpu_one.html | 49.4 kB | | 1a4c00a3 |
| perf_train_special.html | 7.22 kB | | f4f6b92f |
| perf_train_tpu_tf.html | 68 kB | | 08502775 |
| perplexity.html | 39.2 kB | | c938d6f7 |
| philosophy.html | 11.6 kB | | cf84b078 |
| pipeline_gradio.html | 9.88 kB | | 182e1125 |
| pipeline_tutorial.html | 61.6 kB | | 69f4b91d |
| pipeline_webserver.html | 28.4 kB | | bca51e91 |
| pr_checks.html | 44 kB | | 2e4dab64 |
| processors.html | 21.8 kB | | 55ea4cf2 |
| quicktour.html | 54.6 kB | | 95e97a9b |
| run_scripts.html | 34.6 kB | | 757d2adb |
| serialization.html | 22.6 kB | | ab824973 |
| serving.html | 15.1 kB | | e9225f95 |
| task_summary.html | 83.6 kB | | 556d3fd5 |
| tasks_explained.html | 60.3 kB | | 43c595fb |
| testing.html | 250 kB | | 5769be36 |
| tf_xla.html | 26.1 kB | | 403212b6 |
| tflite.html | 13.7 kB | | 108cdb72 |
| tokenizer_summary.html | 65.9 kB | | cc750aea |
| tools.html | 49.6 kB | | a22c8dfe |
| torchscript.html | 28.3 kB | | 171957f2 |
| trainer.html | 72.4 kB | | efa1f84e |
| training.html | 36.7 kB | | 40218282 |
| troubleshooting.html | 47 kB | | 412792f2 |
