Inferensi, Deployment & Runtime

Hugging Face Transformers

huggingface/transformers

A model-definition framework for state-of-the-art machine learning models across text, vision, audio, and multimodal domains, supporting both inference and training.

★ 163,3KBintang
⑂ 34,1KFork
2343Isu terbuka
PythonBahasa
Apache-2.0Lisensi
Q@project.QualityScoreSkor editorial

Tangkapan layar proyek

Tangkapan layar Hugging Face Transformers Tangkapan layar Hugging Face Transformers

Ringkasan

Transformers serves as a centralized model-definition framework that ensures compatibility across the broader machine learning ecosystem. By standardizing model definitions, it allows seamless integration with various training frameworks like Axolotl, Unsloth, DeepSpeed, and PyTorch-Lightning, as well as inference engines such as vLLM, SGLang, and TGI. The library provides a unified API with minimal abstractions, making it accessible for researchers and developers to leverage over 1 million pretrained model checkpoints available on the Hugging Face Hub.

Fitur utama

  • Unified API for pretrained models across text, vision, audio, and multimodal tasks
  • Compatibility with major training frameworks and inference engines
  • Access to over 1 million model checkpoints on the Hugging Face Hub
  • High-level Pipeline API for easy inference across modalities
  • Support for model customization and exposure of model internals

Persyaratan, instalasi, dan mulai cepat

Create and activate a virtual environment using venv or uv. Install Transformers with PyTorch support via pip using 'pip install "transformers[torch]"' or via uv using 'uv pip install "transformers[torch]"'. For the latest changes, install from source by cloning the repository and running 'pip install ".[torch]"'.

Penggunaan

Instantiate a pipeline by specifying a task and model, then pass input data to get results. For example, use 'pipeline(task="text-generation", model="Qwen/Qwen2.5-1.5B")' for text generation. For chat-based interactions, construct a chat history and pass it to the pipeline.

Kompatibilitas model dan kasus penggunaan

Supports a wide range of models including Qwen, Llama, Whisper, DINOv2, BLIP, Mixtral, BART, T5, Gemma, and many others across various modalities.

Catatan lisensi dan risiko

Licensed under the Apache License, Version 2.0.

Editorial verification 2026-08-09: repository URL, owner, description, license and repository statistics were reviewed. License metadata: Apache-2.0. README was fetched for the channel draft; re-check repository dependencies, releases and model terms before production use.

Rilis dan pemeliharaan

Not stated in the repository metadata.

OpenVINO

openvinotoolkit/openvino

★ 10,6KC++

GPUStack

gpustack/gpustack

★ 5,4KPython