| _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 | | 9e785dae |
| add_new_model.html | 136 kB | | e5df551f |
| add_new_pipeline.html | 46.2 kB | | 8d975fdb |
| agents.html | 50.4 kB | | 3de5a2b0 |
| attention.html | 24 kB | | ce683231 |
| attention_interface.html | 24.6 kB | | fc12c47d |
| backbones.html | 24.9 kB | | dbff9511 |
| cache_explanation.html | 18.6 kB | | 55edc73f |
| chat_extras.html | 45.7 kB | | 69602fa2 |
| chat_templating.html | 50.2 kB | | be1f01f1 |
| chat_templating_multimodal.html | 36.8 kB | | de7d3f8a |
| chat_templating_writing.html | 61.6 kB | | 8f978e0f |
| community.html | 43.2 kB | | 27e39499 |
| contributing.html | 72.7 kB | | 636054a0 |
| conversations.html | 30.6 kB | | 83d35eac |
| custom_models.html | 46.4 kB | | d4de8fa5 |
| debugging.html | 65.3 kB | | dafa37db |
| deepspeed.html | 134 kB | | 69ef2299 |
| executorch.html | 10 kB | | ada4b666 |
| fast_tokenizers.html | 71.9 kB | | 0798a177 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| feature_extractors.html | 38.9 kB | | be5acc80 |
| fsdp.html | 34.5 kB | | 12ebdc65 |
| generation_features.html | 17.8 kB | | 7f656b5a |
| generation_strategies.html | 60.6 kB | | dbcc1388 |
| gguf.html | 9.58 kB | | a7dcb702 |
| glossary.html | 152 kB | | 42fcb9e4 |
| gpu_selection.html | 19.2 kB | | 54bfd5fa |
| how_to_hack_models.html | 28.7 kB | | ba68a300 |
| hpo_train.html | 18.9 kB | | f652c7ec |
| image_processors.html | 40.7 kB | | 40958c72 |
| index.html | 9.48 kB | | 3657eb28 |
| installation.html | 42 kB | | e7f08494 |
| kv_cache.html | 71 kB | | 8b8b0954 |
| llm_optims.html | 45.8 kB | | 18385f44 |
| llm_tutorial.html | 56.5 kB | | d8ff04f6 |
| llm_tutorial_optimization.html | 246 kB | | 4c87f8ab |
| model_memory_anatomy.html | 39.6 kB | | 29fa71db |
| model_sharing.html | 36.6 kB | | 9d0a5e75 |
| model_summary.html | 43.8 kB | | b34c6df3 |
| models.html | 57.9 kB | | ed035420 |
| modular_transformers.html | 107 kB | | 09b5e0ef |
| notebooks.html | 70.2 kB | | 0a789e92 |
| objects.inv | 42.9 kB | | 4aaa082e |
| optimizers.html | 30.4 kB | | 7f405b12 |
| pad_truncation.html | 10.5 kB | | 6bfbb54c |
| peft.html | 29.1 kB | | d2f0df23 |
| perf_hardware.html | 14.6 kB | | 2c423e00 |
| perf_infer_cpu.html | 22.4 kB | | e3a29c25 |
| perf_infer_gpu_multi.html | 12.2 kB | | fe5385e4 |
| perf_infer_gpu_one.html | 47.4 kB | | 47f13202 |
| perf_torch_compile.html | 15.9 kB | | 4012fa41 |
| perf_train_cpu.html | 14.2 kB | | 3ff463a7 |
| perf_train_cpu_many.html | 40.3 kB | | 9fde1c2d |
| perf_train_gpu_many.html | 29 kB | | 51df1815 |
| perf_train_gpu_one.html | 49.4 kB | | 24b94d75 |
| perf_train_special.html | 7.22 kB | | 721ebb2b |
| perf_train_tpu_tf.html | 68 kB | | e54dcc4a |
| perplexity.html | 39.2 kB | | f2878250 |
| philosophy.html | 11.6 kB | | c953f844 |
| pipeline_gradio.html | 9.88 kB | | 5c1de162 |
| pipeline_tutorial.html | 61.6 kB | | e19412db |
| pipeline_webserver.html | 28.4 kB | | ca517203 |
| pr_checks.html | 44 kB | | fccc542b |
| processors.html | 21.8 kB | | 069a77c7 |
| quicktour.html | 54.6 kB | | 2f4e9650 |
| run_scripts.html | 34.6 kB | | 8bf7b018 |
| serialization.html | 22.6 kB | | 288fdc98 |
| serving.html | 15.1 kB | | c73053af |
| task_summary.html | 83.6 kB | | a1d4b3be |
| tasks_explained.html | 60.3 kB | | 5b00499f |
| testing.html | 250 kB | | c9360a63 |
| tf_xla.html | 26.1 kB | | 2d756796 |
| tflite.html | 13.7 kB | | 9a775204 |
| tokenizer_summary.html | 65.9 kB | | a1e85e27 |
| tools.html | 49.6 kB | | b124f524 |
| torchscript.html | 28.3 kB | | a96b6f04 |
| trainer.html | 72.4 kB | | 9bbb4507 |
| training.html | 36.7 kB | | d4623956 |
| troubleshooting.html | 47 kB | | f8b3218d |
