SetFit is a promising solution for a common modeling problem: how to deal with lack of labeled data for training. Developed with Hugging Face’s research partners at Intel Labs and the UKP Lab, SetFit is an efficient framework for few-shot fine-tuning of Sentence Transformers models. SetFit achieves high accuracy with little labeled data – for example, SetFit outperforms GPT-3.5 in 3-shot prompting and with 5 shot it also outperforms 3-shot GPT-4 on the Banking 77 financial intent dataset. Compared to […]

Today, integrating AI-powered features, particularly leveraging Large Language Models (LLMs), has become increasingly prevalent across various tasks such as text generation, classification, image-to-text, image-to-image transformations, etc. Developers are increasingly recognizing these applications’ potential benefits, particularly in enhancing core tasks such as scriptwriting, web development, and, now, interfacing with data. Historically, crafting insightful SQL queries for data analysis was primarily the domain of data analysts, SQL developers, data engineers, or professionals in related fields, all navigating the nuances of SQL dialect […]

We are pleased to announce that we are partnering with Wiz with the goal of improving security across our platform and the AI/ML ecosystem at large. Wiz researchers collaborated with Hugging Face on the security of our platform and shared their findings. Wiz is a cloud security company that helps their customers build and maintain software in a secure manner. Along with the publication of this research, we are taking the opportunity to highlight some related Hugging Face security improvements. […]

AI Policy at Hugging Face is a multidisciplinary and cross-organizational workstream. Instead of being part of a vertical communications or global affairs organization, our policy work is rooted in the expertise of our many researchers and developers, from Ethics and Society Regulars and the legal team to machine learning engineers working on healthcare, art, and evaluations. What we work on is informed by our Hugging Face community needs and experiences on the Hub. We champion responsible openness, investing heavily in […]

CodeGemma is a family of open-access versions of Gemma specialized in code, and we’re excited to collaborate with Google on its release to make it as accessible as possible.🤗 CodeGemma comes in three flavors: A 2B base model specialized in infilling and open-ended generation. A 7B base model trained with both code infilling and natural language. A 7B instruct model a user can chat with about code. We’ve collaborated with Google to ensure the best integration into the Hugging Face […]

Today, we are thrilled to announce the launch of Deploy on Google Cloud, a new integration on the Hugging Face Hub to deploy thousands of foundation models easily to Google Cloud using Vertex AI or Google Kubernetes Engine (GKE).    

This blog post was written on April 2024 and provides a great introduction to internals of vision language models, an overview of existing suite of vision language models and how to fine-tune them. We have written an April    

We are excited to release Idefics2, a general multimodal model that takes as input arbitrary sequences of texts and images, and generates text responses. It can answer questions about images, describe visual content, create stories grounded in multiple images, extract information from documents, and perform basic arithmetic operations. Idefics2 improves upon Idefics1: with 8B parameters, an open license (Apache 2.0), and enhanced OCR (Optical Character Recognition) capabilities, Idefics2 is a strong foundation for the community working on multimodality. Its performance […]

This is a guest blog post by the Ryght team. Who is Ryght? Ryght    

This is a guest blog post by the Zama team. Zama is an open source cryptography company building state-of-the-art FHE solutions for blockchain and AI. Eighteen months ago, Zama started Concrete ML, a privacy-preserving ML framework with bindings to traditional ML frameworks such as scikit-learn, ONNX, PyTorch, and TensorFlow. To ensure privacy for users’ data, Zama uses