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    

We are excited to introduce the LiveCodeBench leaderboard, based on LiveCodeBench, a new benchmark developed by researchers from UC Berkeley, MIT, and Cornell for measuring LLMs’ code generation capabilities. LiveCodeBench collects coding problems over time from various coding contest platforms, annotating problems with their release dates. Annotations are used to evaluate models on problem sets released in different time windows, allowing an “evaluation over time” strategy that helps detect and prevent contamination. In addition to the usual code generation task, […]

In this post, I will show you how you can build a functional AI application quickly with Gradio’s reload mode. But before we get to that, I want to explain what reload mode does and why Gradio implements its own auto-reloading logic. If you are already familiar with Gradio and want to get to building, please skip to the third

Meta’s Llama 3, the next iteration of the open-access Llama family, is now released and available at Hugging Face. It’s great to see Meta continuing its commitment to open AI, and we’re excited to fully support the launch with comprehensive integration in the Hugging Face ecosystem. Llama 3 comes in two sizes: 8B for efficient deployment and development on consumer-size GPU, and 70B for large-scale AI native applications. Both come in base and instruction-tuned variants. In addition to the 4 […]

Over the years, Large Language Models (LLMs) have emerged as a groundbreaking technology with immense potential to revolutionize various aspects of healthcare. These models, such as GPT-3, GPT-4 and Med-PaLM 2 have demonstrated remarkable capabilities in understanding and generating human-like text, making them valuable tools for tackling complex medical tasks and improving patient care. They have notably shown promise in various medical applications, such as medical question-answering (QA), dialogue systems, and text generation. Moreover, with the exponential growth of electronic […]