| _app | | | 572 items |
| internal | | | 10 items |
| main_classes | | | 22 items |
| model_doc | | | 342 items |
| quantization | | | 19 items |
| tasks | | | 30 items |
| _redirects.yml | 128 Bytes | | 03cac062 |
| _toctree.yml | 31.2 kB | | a88a82a1 |
| accelerate.html | 27.7 kB | | 12c4c72d |
| add_new_model.html | 136 kB | | c4881871 |
| add_new_pipeline.html | 46.2 kB | | 50429fe6 |
| agents.html | 50.4 kB | | 62a4082e |
| attention.html | 24 kB | | 16df450e |
| attention_interface.html | 24.6 kB | | 98b060c4 |
| backbones.html | 24.9 kB | | ff5544f8 |
| cache_explanation.html | 18.6 kB | | e366e2d8 |
| chat_extras.html | 45.7 kB | | 5f804a40 |
| chat_templating.html | 50.2 kB | | 8ca3caca |
| chat_templating_multimodal.html | 36.8 kB | | 7796ce1d |
| chat_templating_writing.html | 61.6 kB | | 41e4cb69 |
| community.html | 43.2 kB | | 2d36e7a3 |
| contributing.html | 72.7 kB | | 2d825147 |
| conversations.html | 30.6 kB | | c109f844 |
| custom_models.html | 46.4 kB | | 02ba1f06 |
| debugging.html | 65.3 kB | | b380e851 |
| deepspeed.html | 134 kB | | 7bb9b5d2 |
| executorch.html | 10 kB | | fbcab19d |
| fast_tokenizers.html | 71.9 kB | | 469bcc23 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| feature_extractors.html | 38.9 kB | | 0a8dea3e |
| fsdp.html | 34.5 kB | | d934e90a |
| generation_features.html | 17.8 kB | | 3d323e65 |
| generation_strategies.html | 60.6 kB | | 52169692 |
| gguf.html | 9.57 kB | | 86348b52 |
| glossary.html | 152 kB | | 3a25b9cf |
| gpu_selection.html | 19.2 kB | | 84bf786f |
| how_to_hack_models.html | 28.7 kB | | 644af417 |
| hpo_train.html | 18.9 kB | | 4c7841c3 |
| image_processors.html | 40.7 kB | | 0faeec54 |
| index.html | 9.48 kB | | 565f09c5 |
| installation.html | 42 kB | | c3836292 |
| kv_cache.html | 71 kB | | 134a6959 |
| llm_optims.html | 45.8 kB | | b69ad698 |
| llm_tutorial.html | 56.5 kB | | 9aeabe52 |
| llm_tutorial_optimization.html | 246 kB | | c0293148 |
| model_memory_anatomy.html | 39.6 kB | | 7cd37afa |
| model_sharing.html | 36.6 kB | | ed003da8 |
| model_summary.html | 43.8 kB | | 2433425c |
| models.html | 57.9 kB | | 55016794 |
| modular_transformers.html | 107 kB | | fdd6b551 |
| notebooks.html | 70.2 kB | | 6e06d9c6 |
| objects.inv | 42.8 kB | | ba4b64f5 |
| optimizers.html | 30.4 kB | | dcefc1cb |
| pad_truncation.html | 10.5 kB | | b04ea19e |
| peft.html | 29.1 kB | | ed37cdea |
| perf_hardware.html | 14.6 kB | | 5a76d0a6 |
| perf_infer_cpu.html | 22.4 kB | | b117563d |
| perf_infer_gpu_multi.html | 12.2 kB | | a564c150 |
| perf_infer_gpu_one.html | 47.4 kB | | 0fc90161 |
| perf_torch_compile.html | 15.9 kB | | 95c39e83 |
| perf_train_cpu.html | 14.2 kB | | c4819383 |
| perf_train_cpu_many.html | 40.3 kB | | 250c0371 |
| perf_train_gpu_many.html | 29 kB | | 2e35f3ab |
| perf_train_gpu_one.html | 49.4 kB | | ca27499f |
| perf_train_special.html | 7.22 kB | | d6523d66 |
| perf_train_tpu_tf.html | 68 kB | | fa6f739f |
| perplexity.html | 39.2 kB | | 2c91cd1f |
| philosophy.html | 11.6 kB | | 4943ce8f |
| pipeline_gradio.html | 9.88 kB | | 87c8ba50 |
| pipeline_tutorial.html | 61.6 kB | | 80a813c1 |
| pipeline_webserver.html | 28.4 kB | | b4932f88 |
| pr_checks.html | 44 kB | | 2d93896c |
| processors.html | 21.8 kB | | e677b069 |
| quicktour.html | 54.6 kB | | 2fc6c7f6 |
| run_scripts.html | 34.6 kB | | 0f7aa0db |
| serialization.html | 22.6 kB | | 01b2a396 |
| serving.html | 15.1 kB | | dbd59375 |
| task_summary.html | 83.6 kB | | c79f2b57 |
| tasks_explained.html | 60.3 kB | | 9b02e576 |
| testing.html | 250 kB | | 483f6686 |
| tf_xla.html | 26.1 kB | | bd25d8b0 |
| tflite.html | 13.7 kB | | 1ad73388 |
| tokenizer_summary.html | 65.9 kB | | 2f24c472 |
| tools.html | 49.6 kB | | f29f704a |
| torchscript.html | 28.3 kB | | 0baabcac |
| trainer.html | 72.4 kB | | eebfd4ff |
| training.html | 36.7 kB | | c6b08178 |
| troubleshooting.html | 47 kB | | eb7c952f |
