| _app | | | 514 items |
| internal | | | 9 items |
| main_classes | | | 22 items |
| model_doc | | | 334 items |
| quantization | | | 18 items |
| tasks | | | 30 items |
| _redirects.yml | 128 Bytes | | 03cac062 |
| _toctree.yml | 30.4 kB | | 179f442d |
| accelerate.html | 27.7 kB | | f3d53ec9 |
| add_new_model.html | 126 kB | | 58c12924 |
| add_new_pipeline.html | 46.2 kB | | 1d4aad31 |
| agents.html | 50.4 kB | | e7d20a51 |
| attention.html | 37.8 kB | | 097f742d |
| backbones.html | 24.9 kB | | 86027024 |
| cache_explanation.html | 18.6 kB | | 20c73195 |
| chat_extras.html | 45.7 kB | | 10caabf2 |
| chat_templating.html | 50.2 kB | | fffa85b9 |
| chat_templating_multimodal.html | 36.8 kB | | e8d13ea4 |
| chat_templating_writing.html | 61.6 kB | | 9e729a28 |
| community.html | 43.3 kB | | 7d374feb |
| contributing.html | 72.6 kB | | fe627262 |
| conversations.html | 30.6 kB | | e33236b5 |
| custom_models.html | 46.4 kB | | 363fd2cb |
| debugging.html | 65.3 kB | | 033a0669 |
| deepspeed.html | 133 kB | | bf29da77 |
| executorch.html | 10 kB | | 262818e4 |
| fast_tokenizers.html | 71.9 kB | | 5272b287 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| feature_extractors.html | 38.9 kB | | b442d2ba |
| fsdp.html | 34.5 kB | | 73e9a312 |
| generation_features.html | 17.8 kB | | cee9e835 |
| generation_strategies.html | 60.6 kB | | 3e97768e |
| gguf.html | 9.25 kB | | 8e0790e8 |
| glossary.html | 152 kB | | df208b56 |
| gpu_selection.html | 19.2 kB | | a8fb82fc |
| how_to_hack_models.html | 28.7 kB | | c124eb48 |
| hpo_train.html | 18.9 kB | | 32736453 |
| image_processors.html | 40.7 kB | | ea887dc1 |
| index.html | 9.83 kB | | d003918f |
| installation.html | 41.9 kB | | b87cf953 |
| kv_cache.html | 71 kB | | d9881b3d |
| llm_optims.html | 45.8 kB | | af1e56ce |
| llm_tutorial.html | 56.5 kB | | 435f3603 |
| llm_tutorial_optimization.html | 246 kB | | f7c81057 |
| model_memory_anatomy.html | 39.6 kB | | 4185bf45 |
| model_sharing.html | 36.6 kB | | 07d6ff7e |
| model_summary.html | 43.8 kB | | 0beab4d5 |
| models.html | 57.8 kB | | 894a838d |
| modular_transformers.html | 107 kB | | eee003a8 |
| notebooks.html | 70.2 kB | | 3b93e0bf |
| objects.inv | 42.1 kB | | 1b90d839 |
| optimizers.html | 30.4 kB | | a1333542 |
| pad_truncation.html | 10.6 kB | | 238c0249 |
| peft.html | 29.1 kB | | be19ec9f |
| perf_hardware.html | 14.7 kB | | d394470c |
| perf_infer_cpu.html | 22.4 kB | | 4324cc0f |
| perf_infer_gpu_multi.html | 10.7 kB | | fc47e4cc |
| perf_infer_gpu_one.html | 47.4 kB | | 8475a67b |
| perf_torch_compile.html | 15.9 kB | | 9ad122f9 |
| perf_train_cpu.html | 14.2 kB | | 39f98ea8 |
| perf_train_cpu_many.html | 40.3 kB | | f1010f8c |
| perf_train_gpu_many.html | 28.7 kB | | 94b8b8cd |
| perf_train_gpu_one.html | 49.4 kB | | 7d2c18e3 |
| perf_train_special.html | 7.22 kB | | 8c9dc535 |
| perf_train_tpu_tf.html | 68 kB | | 7a3b2c21 |
| perplexity.html | 39.2 kB | | 2b7b0999 |
| philosophy.html | 11.6 kB | | 4f937950 |
| pipeline_gradio.html | 9.89 kB | | 58365dbf |
| pipeline_tutorial.html | 61.6 kB | | f16b28ca |
| pipeline_webserver.html | 28.4 kB | | 7f259a30 |
| pr_checks.html | 44 kB | | 9e80c6df |
| processors.html | 21.8 kB | | 10b35749 |
| quicktour.html | 54.6 kB | | 5c239ff7 |
| run_scripts.html | 34.6 kB | | 8d7ceb21 |
| serialization.html | 22.6 kB | | 1b31291c |
| task_summary.html | 83.6 kB | | 1ce1f4a8 |
| tasks_explained.html | 60.3 kB | | 880d75fa |
| testing.html | 250 kB | | baeae081 |
| tf_xla.html | 26.1 kB | | ba58e5ad |
| tflite.html | 13.7 kB | | 6b18a0b0 |
| tokenizer_summary.html | 65.9 kB | | 517d9082 |
| tools.html | 49.6 kB | | 7fd35ff5 |
| torchscript.html | 28.3 kB | | 1b0e54fc |
| trainer.html | 72.4 kB | | 318ae556 |
| training.html | 36.7 kB | | e7175037 |
| troubleshooting.html | 47 kB | | 88e329c1 |
