Developer Resources from Intel and Hugging Face*
Intel and Hugging Face* collaborate to optimize the performance of popular models and tools for Intel® hardware and software. The two companies develop and optimize open source tools that enable production AI application deployment, and Intel provides preoptimized models and datasets on the Hugging Face hub. Optimum for Intel® Gaudi® platform simplifies model optimization targeted for Intel CPUs, GPUs, and AI accelerators.
Intel and Hugging Face Case Studies
"At Hugging Face, we are focused on making the latest advancements in AI more accessible to everyone. Making state-of-the-art machine learning models more efficient and cheaper to use is incredibly important to us, and we're proud to partner with Intel to make it easy for the community to get peak CPU performance, faster model training, and advanced AI deployments on powerful Intel hardware devices using our free open source Optimum library, integrating OpenVINO™ toolkit, Intel Neural Compressor, Synapse AI*, and many more powerful solutions of AI Tools."
— Jeff Boudier, product director, Hugging Face
Use Hugging Face Tools with Intel® Platforms
Learn how to get started and how to get the most out of Hugging Face models and tools on Intel-based platforms spanning data centers, cloud, and AI PCs. These joint offerings are based on OpenVINO™ toolkit, AI Tools, and Intel® Gaudi® software.
Multiplatform
- Hugging Face Optimum for Intel
- Hugging Face Optimum Documentation
- Hugging Face Optimum Notebooks
- Post-training Quantization with AutoRound
- Faster Assisted Generation with Dynamic Speculation
- Faster Decoding with Any Assistant Model Using Universal Assisted Generation Techniques
- Speed Up LLM Decoding with Advanced Universal Assisted Generation Techniques
- Introducing Holistically Evaluating Long-context Language Models (HELMET)
AI PC
- Hugging Face Model Hub with OpenVINO Toolkit
- Notebooks for the OpenVINO Toolkit Integration in Hugging Face Optimum for Intel® Gaudi® Processors
- Optimize and Deploy Models with Optimum for Intel and OpenVINO Toolkit Generative AI
- A Chatbot on Your Laptop: Phi-2 on Intel® Core™ Ultra Processors
- Three Minutes to Build a Chatbot on Your AI PC
- Large Model Weights Compression
Data Center and Cloud
- Examples for Hugging Face Optimum for Intel Gaudi Processors
- Build Cost-Efficient Retrieval Augmented Generation (RAG) Applications with Intel Gaudi 2 Processors and Intel® Xeon® Processors
- SetFit Sentence Transformers
- Blazing Fast SetFit Inference with 🤗 Optimum for Intel and Intel Xeon Processors
- CPU-Optimized Embeddings with 🤗 Optimum for Intel and fastRAG
- Text-Generation Pipeline on Intel® Gaudi® 2 AI Accelerators
- The Ultimate Guide to Using Contrastive Language Image Pretraining (CLIP) with an Intel Gaudi 2 Accelerator
- Fine-Tune the Meta* Llama 3.2-Vision-Instruct Multimodal LLM on Intel Accelerators
- Accelerate LLM Inference with Text Generation Inference (TGI) on Intel Gaudi AI Accelerators
- Scale LLMs with Intel Gaudi and Intel Xeon Processors
- How to Benchmark Language Models on 5th Gen Intel® Xeon® CPUs on Google Cloud Platform* Service
More Resources
AI Development Resources
Explore tutorials, training, documentation, and support resources for AI developers.
AI Tools
Download Intel-optimized end-to-end AI tools and frameworks.
Intel® AI Hardware
Learn what type of device best suits your AI workload, spanning CPUs, GPUs, and AI accelerators.