Vibe Coding Discovertransformers
View on GitHub🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Hugging Face Transformers is the model-definition framework for state-of-the-art text, vision, audio, video and multimodal models. It offers a unified Pipeline/Trainer API over 1M+ Hub checkpoints and feeds model definitions to vLLM, llama.cpp and training stacks.
Use Cases
Load and run pretrained models for text, vision, audio and multimodal tasksText generation and chat with LLMsAutomatic speech recognition with WhisperImage classification and visual question answeringFine-tune or train models with a unified Trainer APIServe models via transformers serve and CLI chatProvide shared model definitions consumed by vLLM, SGLang, llama.cpp and MLXBuild RAG and embedding pipelines from Hub checkpoints
Built With
- Language
- Python
- Frameworks
- PyTorch · JAX · TensorFlow · Flax · safetensors · tokenizers · accelerate · vLLM · SGLang · TGI · llama.cpp · MLX · DeepSpeed · FSDP · PyTorch-Lightning · Unsloth
Tags
transformers · model-definition · pretrained-models · llm · multimodal · nlp · computer-vision · audio · speech-recognition · inference · training · fine-tuning · pytorch · model-hub · vlm · pipeline-api