| _app | | | 1,790 items |
| internal | | | 11 items |
| main_classes | | | 22 items |
| model_doc | | | 356 items |
| quantization | | | 22 items |
| tasks | | | 31 items |
| _redirects.yml | 128 Bytes | | 03cac062 |
| _toctree.yml | 32.6 kB | | b274d9ce |
| accelerate.html | 27.9 kB | | 32c1546e |
| add_new_model.html | 136 kB | | c74b6893 |
| add_new_pipeline.html | 46.3 kB | | 98b33824 |
| agents.html | 3.11 kB | | 2d62ecdd |
| attention.html | 24.2 kB | | ab500222 |
| attention_interface.html | 24.7 kB | | 8cd1f1c6 |
| auto_docstring.html | 55.1 kB | | e57bd401 |
| backbones.html | 25 kB | | d3878fcd |
| cache_explanation.html | 18.7 kB | | 78e647f6 |
| chat_extras.html | 45.8 kB | | dff61cbc |
| chat_templating.html | 50.3 kB | | cf03aae0 |
| chat_templating_multimodal.html | 36.7 kB | | 46e96aa5 |
| chat_templating_writing.html | 61.7 kB | | 71910992 |
| community.html | 43.4 kB | | 02ae2c99 |
| contributing.html | 72.8 kB | | 5d67d28f |
| conversations.html | 32.1 kB | | 279b2cbf |
| custom_models.html | 46.5 kB | | 4ad375e8 |
| debugging.html | 65.4 kB | | 1b723e43 |
| deepspeed.html | 134 kB | | 5f62d7b2 |
| executorch.html | 10.1 kB | | 4c1ac5b6 |
| fast_tokenizers.html | 72 kB | | 5e065998 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| feature_extractors.html | 39 kB | | 02fa8f53 |
| fsdp.html | 34.6 kB | | fad60e77 |
| generation_features.html | 17.9 kB | | c08fe0f0 |
| generation_strategies.html | 95.5 kB | | ebabf754 |
| gguf.html | 9.68 kB | | 4b91747a |
| glossary.html | 152 kB | | 70f53653 |
| gpu_selection.html | 19.3 kB | | fa886675 |
| how_to_hack_models.html | 28.8 kB | | 769e14c6 |
| hpo_train.html | 19 kB | | f740bf81 |
| image_processors.html | 40.8 kB | | d6fc5742 |
| index.html | 9.59 kB | | 250306ee |
| installation.html | 42.1 kB | | d8e359ac |
| kv_cache.html | 71.1 kB | | 67b637f6 |
| llm_optims.html | 46 kB | | e1553ff4 |
| llm_tutorial.html | 62 kB | | c97e19c3 |
| llm_tutorial_optimization.html | 246 kB | | 89e538aa |
| model_memory_anatomy.html | 39.8 kB | | 62717a04 |
| model_sharing.html | 36.7 kB | | c9860a95 |
| model_summary.html | 43.9 kB | | 7a967ede |
| models.html | 58 kB | | edc55203 |
| modular_transformers.html | 107 kB | | 798673b6 |
| notebooks.html | 70.3 kB | | 307ecdf2 |
| objects.inv | 44.2 kB | | 1d2cfb5a |
| optimizers.html | 30.5 kB | | 88c98d39 |
| pad_truncation.html | 10.7 kB | | de978577 |
| peft.html | 29.2 kB | | acc08d65 |
| perf_hardware.html | 14.8 kB | | 2c20a075 |
| perf_infer_cpu.html | 22.5 kB | | 8679db79 |
| perf_infer_gpu_multi.html | 12.3 kB | | 6cd095a3 |
| perf_infer_gpu_one.html | 47.5 kB | | dc6992a7 |
| perf_torch_compile.html | 16 kB | | 529a577c |
| perf_train_cpu.html | 14.3 kB | | 1dc40e11 |
| perf_train_cpu_many.html | 40.4 kB | | 1cd6ea0e |
| perf_train_gaudi.html | 8.96 kB | | 338b334d |
| perf_train_gpu_many.html | 29.1 kB | | 1b311e5d |
| perf_train_gpu_one.html | 49.5 kB | | e199696a |
| perf_train_special.html | 7.32 kB | | e1b639a5 |
| perf_train_tpu_tf.html | 68.2 kB | | ab8c46e6 |
| perplexity.html | 39.3 kB | | 880d452e |
| philosophy.html | 11.7 kB | | a41f2236 |
| pipeline_gradio.html | 9.99 kB | | 468c1660 |
| pipeline_tutorial.html | 61.7 kB | | 320d96a6 |
| pipeline_webserver.html | 30.4 kB | | 547d3b94 |
| pr_checks.html | 44.1 kB | | da2e7931 |
| processors.html | 21.9 kB | | 66cd94ea |
| quicktour.html | 54.7 kB | | d83ba98d |
| run_scripts.html | 34.7 kB | | 5d5098f0 |
| serialization.html | 22.7 kB | | e76c4b20 |
| serving.html | 15.2 kB | | 1c947f7e |
| task_summary.html | 83.7 kB | | e08ca254 |
| tasks_explained.html | 60.4 kB | | bc5d6bbd |
| testing.html | 250 kB | | dc2f1e9b |
| tf_xla.html | 26.2 kB | | 562cc5dd |
| tflite.html | 13.8 kB | | 4568daab |
| tokenizer_summary.html | 66 kB | | 9451256e |
| tools.html | 3.11 kB | | e3c11d05 |
| torchscript.html | 28.4 kB | | 2eb8b23f |
| trainer.html | 69.9 kB | | 50c5cdf7 |
| training.html | 36.8 kB | | cd07d0bb |
| troubleshooting.html | 47.2 kB | | c5324f9c |
| video_processors.html | 11.7 kB | | 6594d67b |
