| _app | | | 479 items |
| internal | | | 9 items |
| main_classes | | | 21 items |
| model_doc | | | 308 items |
| quantization | | | 14 items |
| tasks | | | 30 items |
| _redirects.yml | 128 Bytes | | 03cac062 |
| _toctree.yml | 29 kB | | f88c2e2d |
| accelerate.html | 28.1 kB | | 7f533a22 |
| add_new_model.html | 140 kB | | f0935f96 |
| add_new_pipeline.html | 38.3 kB | | aa46309b |
| agents.html | 74.1 kB | | d6b66367 |
| agents_advanced.html | 45.7 kB | | fc61cb59 |
| attention.html | 24.1 kB | | 525d436b |
| autoclass_tutorial.html | 46.1 kB | | d5ab1540 |
| benchmarks.html | 65.9 kB | | 7d2c2066 |
| bertology.html | 5.97 kB | | 0c836aad |
| big_models.html | 43.6 kB | | 011bc543 |
| chat_templating.html | 188 kB | | ec73e7f6 |
| community.html | 43.3 kB | | 4d36ba12 |
| contributing.html | 72.8 kB | | 8c15f35f |
| conversations.html | 48.5 kB | | dd473b5a |
| create_a_model.html | 98.9 kB | | b8c9866b |
| custom_models.html | 58.6 kB | | 4ba88fd2 |
| debugging.html | 84.1 kB | | 67aa433b |
| deepspeed.html | 150 kB | | 85d00f45 |
| fast_tokenizers.html | 15.9 kB | | 1d728dff |
| favicon.png | 1.57 kB | | 6e06dd7b |
| fsdp.html | 34.7 kB | | 100892eb |
| generation_strategies.html | 101 kB | | f1a8194d |
| gguf.html | 16.7 kB | | 658f4ba5 |
| glossary.html | 152 kB | | 092b23bb |
| how_to_hack_models.html | 36.1 kB | | d99258fb |
| hpo_train.html | 31.5 kB | | 9cfb4355 |
| index.html | 61.4 kB | | 77b6bc04 |
| installation.html | 56.5 kB | | e8cad689 |
| kv_cache.html | 86.7 kB | | 9833c0e8 |
| llm_optims.html | 51.8 kB | | 68f424cb |
| llm_tutorial.html | 56.7 kB | | cc44126a |
| llm_tutorial_optimization.html | 246 kB | | 87324299 |
| model_memory_anatomy.html | 39.6 kB | | 02f4cf02 |
| model_sharing.html | 65 kB | | 17dd80e8 |
| model_summary.html | 43.8 kB | | 4daf706e |
| modular_transformers.html | 40.5 kB | | f83ddcc4 |
| multilingual.html | 39.4 kB | | 3a11061a |
| notebooks.html | 71.9 kB | | b8e5a6f0 |
| objects.inv | 40.7 kB | | 13133731 |
| pad_truncation.html | 10.6 kB | | 27d15c56 |
| peft.html | 108 kB | | 3733f80a |
| perf_hardware.html | 25.2 kB | | 5ee47c9d |
| perf_infer_cpu.html | 24.9 kB | | d084d89e |
| perf_infer_gpu_multi.html | 10.9 kB | | 2cc32de9 |
| perf_infer_gpu_one.html | 83.6 kB | | fb85c95e |
| perf_torch_compile.html | 67.8 kB | | a5408015 |
| perf_train_cpu.html | 16.3 kB | | 9a2775b9 |
| perf_train_cpu_many.html | 51.4 kB | | 743d25d2 |
| perf_train_gpu_many.html | 87.2 kB | | 77fbc7dc |
| perf_train_gpu_one.html | 91.4 kB | | 7ab17ad9 |
| perf_train_special.html | 10.2 kB | | 2e6da065 |
| perf_train_tpu_tf.html | 40.8 kB | | 3e78aa6f |
| performance.html | 12.9 kB | | deee2b66 |
| perplexity.html | 39 kB | | 621d447c |
| philosophy.html | 11.6 kB | | 12014c09 |
| pipeline_tutorial.html | 75.4 kB | | 245b0822 |
| pipeline_webserver.html | 25.2 kB | | 83cd53fb |
| pr_checks.html | 44 kB | | 9377fe1b |
| preprocessing.html | 129 kB | | fdccf074 |
| quicktour.html | 156 kB | | 235a8270 |
| run_scripts.html | 68.7 kB | | 913b3386 |
| sagemaker.html | 5.86 kB | | 56ba7799 |
| serialization.html | 42.4 kB | | dcd46883 |
| task_summary.html | 83.6 kB | | 3ab38651 |
| tasks_explained.html | 60.3 kB | | 0a118532 |
| testing.html | 250 kB | | a66ae29b |
| tf_xla.html | 34.7 kB | | 1f333e93 |
| tflite.html | 11.8 kB | | 760b3d11 |
| tiktoken.html | 9.44 kB | | 6c52a074 |
| tokenizer_summary.html | 65.9 kB | | f17eb713 |
| torchscript.html | 37.8 kB | | 1b4e0d70 |
| trainer.html | 97.8 kB | | 1a428889 |
| training.html | 98.5 kB | | e387a286 |
| troubleshooting.html | 47 kB | | 318ad7da |
