| _app | | | 1,105 items |
| internal | | | 9 items |
| main_classes | | | 21 items |
| model_doc | | | 333 items |
| quantization | | | 18 items |
| tasks | | | 30 items |
| _redirects.yml | 128 Bytes | | 03cac062 |
| _toctree.yml | 31 kB | | b157ae9e |
| accelerate.html | 28.1 kB | | bbf46bad |
| add_new_model.html | 140 kB | | 57a260e7 |
| add_new_pipeline.html | 41.2 kB | | b23ebe66 |
| agents.html | 4.44 kB | | a3b77c8c |
| agents_advanced.html | 4.75 kB | | 9551f5e2 |
| attention.html | 24.1 kB | | 2abba07d |
| autoclass_tutorial.html | 46.9 kB | | af36e95a |
| bertology.html | 5.97 kB | | fe404fd9 |
| big_models.html | 43.6 kB | | 05272d4a |
| chat_template_advanced.html | 84.6 kB | | b3089049 |
| chat_template_basics.html | 48.5 kB | | 46a82436 |
| chat_template_multimodal.html | 50.3 kB | | 5d78e6d0 |
| chat_template_tools_and_documents.html | 58.8 kB | | 8015f6cd |
| community.html | 43.3 kB | | e290ca53 |
| contributing.html | 72.6 kB | | df81e76c |
| conversations.html | 48.5 kB | | d211f2e3 |
| create_a_model.html | 98.9 kB | | 01faa482 |
| custom_models.html | 58.6 kB | | 2b0a52a7 |
| debugging.html | 84.1 kB | | 561ee052 |
| deepspeed.html | 154 kB | | 21d4b6e0 |
| fast_tokenizers.html | 15.9 kB | | e61b39d0 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| fsdp.html | 34.7 kB | | e9ab0bfc |
| generation_strategies.html | 106 kB | | d5135b82 |
| gguf.html | 16.7 kB | | 40a31057 |
| glossary.html | 152 kB | | f1a4ddc3 |
| how_to_hack_models.html | 40.9 kB | | 1f9eb306 |
| hpo_train.html | 31.5 kB | | 9df47cf5 |
| index.html | 65.7 kB | | 34b6cf34 |
| installation.html | 66.4 kB | | 8eeaabed |
| kv_cache.html | 88.2 kB | | 5aa47d19 |
| llm_optims.html | 52 kB | | 217dc78b |
| llm_tutorial.html | 57.7 kB | | e6260f84 |
| llm_tutorial_optimization.html | 246 kB | | 097e5e91 |
| model_memory_anatomy.html | 39.6 kB | | 2dcb2b7e |
| model_sharing.html | 65 kB | | 4fc1d517 |
| model_summary.html | 43.8 kB | | 2089f4dc |
| modular_transformers.html | 124 kB | | 8d6d33d7 |
| multilingual.html | 39.4 kB | | 011f091f |
| notebooks.html | 70.2 kB | | 131dd2a2 |
| objects.inv | 42.4 kB | | 1bfe4204 |
| pad_truncation.html | 10.6 kB | | 992e8a31 |
| peft.html | 110 kB | | 532a79de |
| perf_hardware.html | 25.2 kB | | bffcbba6 |
| perf_infer_cpu.html | 25 kB | | e76f3c53 |
| perf_infer_gpu_multi.html | 12.6 kB | | d1130e34 |
| perf_infer_gpu_one.html | 87.8 kB | | 6d95ca93 |
| perf_torch_compile.html | 68.4 kB | | 9f7bde4e |
| perf_train_cpu.html | 16.4 kB | | a837230d |
| perf_train_cpu_many.html | 51.5 kB | | 79712958 |
| perf_train_gpu_many.html | 87.5 kB | | 4bc6d2ef |
| perf_train_gpu_one.html | 91.3 kB | | 84bb6528 |
| perf_train_special.html | 10.2 kB | | 125c1dcf |
| perf_train_tpu_tf.html | 40.8 kB | | 3e0cfe22 |
| performance.html | 12.9 kB | | 0d210680 |
| perplexity.html | 39.2 kB | | f7c69617 |
| philosophy.html | 11.6 kB | | e0b9d6f0 |
| pipeline_tutorial.html | 75.6 kB | | 1bde7327 |
| pipeline_webserver.html | 25.2 kB | | d5c6c092 |
| pr_checks.html | 44 kB | | 868ca884 |
| preprocessing.html | 129 kB | | 1da13856 |
| quicktour.html | 162 kB | | 9b2d0b4f |
| run_scripts.html | 68.7 kB | | a7da1b9c |
| sagemaker.html | 5.86 kB | | cdd4606d |
| serialization.html | 42.5 kB | | 754ff494 |
| task_summary.html | 83.6 kB | | b7451b70 |
| tasks_explained.html | 60.3 kB | | 09e66de0 |
| testing.html | 250 kB | | 823b1b6b |
| tf_xla.html | 34.7 kB | | 116da61a |
| tflite.html | 11.8 kB | | a3207cf4 |
| tiktoken.html | 14.9 kB | | 139fcf38 |
| tokenizer_summary.html | 65.9 kB | | 8bb79fa2 |
| torchscript.html | 37.8 kB | | ceb3e9b9 |
| trainer.html | 109 kB | | f0e7ce5a |
| training.html | 99 kB | | 86b059f1 |
| troubleshooting.html | 47 kB | | 930309bc |
