| _app | | | 1,061 items |
| internal | | | 11 items |
| main_classes | | | 22 items |
| model_doc | | | 349 items |
| quantization | | | 21 items |
| tasks | | | 31 items |
| _redirects.yml | 128 Bytes | | 03cac062 |
| _toctree.yml | 31.8 kB | | 3afeb5e5 |
| accelerate.html | 27.9 kB | | 6e3d4c2a |
| add_new_model.html | 136 kB | | 2070d36e |
| add_new_pipeline.html | 46.3 kB | | d81c15da |
| agents.html | 3.11 kB | | b9ac98a6 |
| attention.html | 24.2 kB | | 6a6bae1b |
| attention_interface.html | 24.7 kB | | ad8f09ee |
| backbones.html | 25 kB | | 3d915cd9 |
| cache_explanation.html | 18.7 kB | | 09e9ebaa |
| chat_extras.html | 45.8 kB | | 3aadf5a0 |
| chat_templating.html | 50.3 kB | | f2f09835 |
| chat_templating_multimodal.html | 36.7 kB | | 4773c473 |
| chat_templating_writing.html | 61.7 kB | | 1ae9c203 |
| community.html | 43.4 kB | | b611d807 |
| contributing.html | 72.8 kB | | dad53baf |
| conversations.html | 30.7 kB | | 416181df |
| custom_models.html | 46.5 kB | | 8bbdee9c |
| debugging.html | 65.4 kB | | 99c1577e |
| deepspeed.html | 134 kB | | bd93c7d8 |
| executorch.html | 10.1 kB | | 86487357 |
| fast_tokenizers.html | 72 kB | | 5edc2ed7 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| feature_extractors.html | 39 kB | | 923a5acc |
| fsdp.html | 34.6 kB | | d0cf4b53 |
| generation_features.html | 17.9 kB | | faacedb7 |
| generation_strategies.html | 60.7 kB | | f92d1c17 |
| gguf.html | 9.68 kB | | 255b33fb |
| glossary.html | 152 kB | | a4bfa6ed |
| gpu_selection.html | 19.3 kB | | 7d864229 |
| how_to_hack_models.html | 28.8 kB | | 384263c7 |
| hpo_train.html | 19 kB | | 1dbe99a1 |
| image_processors.html | 40.8 kB | | 5852c62c |
| index.html | 9.59 kB | | 6657c954 |
| installation.html | 42.1 kB | | b8fc1d2f |
| kv_cache.html | 71.1 kB | | d8e89e3d |
| llm_optims.html | 46 kB | | c0c9e953 |
| llm_tutorial.html | 56.6 kB | | 96da004a |
| llm_tutorial_optimization.html | 246 kB | | a12ec5bd |
| model_memory_anatomy.html | 39.8 kB | | 2f2c44fc |
| model_sharing.html | 36.7 kB | | 9f2416d1 |
| model_summary.html | 43.9 kB | | 06e61ea6 |
| models.html | 58 kB | | 7e78daa0 |
| modular_transformers.html | 107 kB | | 0efa017e |
| notebooks.html | 70.3 kB | | 1696fe1e |
| objects.inv | 43.3 kB | | fc049094 |
| optimizers.html | 30.5 kB | | 70e64ee1 |
| pad_truncation.html | 10.7 kB | | df338692 |
| peft.html | 29.2 kB | | 87310505 |
| perf_hardware.html | 14.8 kB | | e6b26ff0 |
| perf_infer_cpu.html | 22.5 kB | | bdbdf3fe |
| perf_infer_gpu_multi.html | 12.3 kB | | 1e754ec0 |
| perf_infer_gpu_one.html | 47.5 kB | | e4ab2ff6 |
| perf_torch_compile.html | 16 kB | | e8a7ff82 |
| perf_train_cpu.html | 14.3 kB | | c18139c8 |
| perf_train_cpu_many.html | 40.4 kB | | a0de5647 |
| perf_train_gpu_many.html | 29.1 kB | | c65cada7 |
| perf_train_gpu_one.html | 49.5 kB | | 9ff1eae0 |
| perf_train_special.html | 7.33 kB | | 5433291f |
| perf_train_tpu_tf.html | 68.2 kB | | 03a1287d |
| perplexity.html | 39.3 kB | | ead7f30c |
| philosophy.html | 11.7 kB | | 8256d736 |
| pipeline_gradio.html | 9.99 kB | | 3e6bb7ed |
| pipeline_tutorial.html | 61.7 kB | | 2eeb5513 |
| pipeline_webserver.html | 30.4 kB | | 8fb510a8 |
| pr_checks.html | 44.1 kB | | 07ae3a68 |
| processors.html | 21.9 kB | | 93f66b64 |
| quicktour.html | 54.7 kB | | cd69bbd6 |
| run_scripts.html | 34.7 kB | | 458116d8 |
| serialization.html | 22.7 kB | | 9454770a |
| serving.html | 15.2 kB | | f666b39b |
| task_summary.html | 83.7 kB | | 8a5c1880 |
| tasks_explained.html | 60.4 kB | | 76835ba4 |
| testing.html | 250 kB | | fe793f92 |
| tf_xla.html | 26.2 kB | | 237347a1 |
| tflite.html | 13.8 kB | | 37bd3dba |
| tokenizer_summary.html | 66 kB | | 318ccf8a |
| tools.html | 3.11 kB | | 88a8d673 |
| torchscript.html | 28.4 kB | | 2e2d3efe |
| trainer.html | 70 kB | | d927c60d |
| training.html | 36.8 kB | | dfb60834 |
| troubleshooting.html | 47.2 kB | | 26611f03 |
