Recently, Argilla and Hugging Face launched Data is Better Together, an experiment to collectively build a preference dataset of prompt rankings. In a few days, we had: 350 community contributors labeling data Over 11,000 prompt    

Models are becoming quite good at understanding text on its own, but what about text in images, which gives important contextual information? For example, navigating a map, or understanding a meme? The ability to reason about the interactions between the text and visual context in images can power many real-world applications, such as AI assistants, or tools to assist the visually impaired. We refer to these tasks as “context-sensitive text-rich visual reasoning tasks”. At the moment, most evaluations of instruction-tuned […]

In the world of web development, turning designs into functional websites usually involves a lot of coding and careful testing. What if we could simplify this process, making it possible to convert web designs into working websites more easily and quickly? WebSight is a new dataset that aims at building AI systems capable of transforming screenshots to HTML code. The challenge Turning a website design or screenshot into HTML code usually needs an experienced developer. But what if    

Embedding models are useful for many applications such as retrieval, reranking, clustering, and classification. The research community has witnessed significant advancements in recent years in embedding models, leading to substantial enhancements in all applications building on semantic representation. Models such as BGE, GTE, and E5 are placed at the top of the MTEB benchmark and in some cases outperform proprietary embedding services. There are a variety of model sizes found in Hugging Face’s Model hub, from lightweight (100-350M parameters) to […]

Quantization is a technique to reduce the computational and memory costs of evaluating Deep Learning Models by representing their weights and activations with low-precision data types like 8-bit integer (int8) instead of the usual 32-bit floating point (float32). Reducing the number of bits means the resulting model requires less memory storage, which is crucial for deploying Large Language Models on consumer devices. It also enables specific optimizations for lower bitwidth datatypes, such as int8 or float8 matrix multiplications on CUDA […]

Update: This service is deprecated and no longer available as of April 10th, 2025. Today, we are thrilled to announce the launch of Train on DGX Cloud, a new service on the Hugging Face Hub, available to Enterprise Hub organizations. Train on DGX Cloud makes it easy to use open models with the accelerated compute infrastructure of NVIDIA DGX Cloud. Together, we built Train on DGX Cloud so that Enterprise Hub users can easily access the latest NVIDIA H100 Tensor […]

The integration of GaLore into the training of large language models (LLMs) marks a significant advancement in the field of deep learning, particularly in terms of memory efficiency and the democratization of AI research. By allowing for the training of billion-parameter models on consumer-grade hardware, reducing memory footprint in optimizer states, and leveraging advanced projection matrix techniques, GaLore opens new horizons for researchers and practitioners with limited access to high-end computational resources. Scaling LLMs with Consumer-Grade Hardware The    

In this blog post, we outline the challenges and solutions involved in generating a synthetic dataset with billions of tokens to replicate Phi-1.5, leading to the creation of Cosmopedia. Synthetic data has become a central topic in Machine Learning. It refers to artificially generated data, for instance by large language models (LLMs), to mimic real-world data. Traditionally, creating datasets for supervised fine-tuning and instruction-tuning required the costly and time-consuming process of hiring human annotators. This practice entailed significant resources, limiting […]

Because of their impressive abilities, large language models (LLMs) require significant computing power, which is seldom available on personal computers. Consequently, we have no choice but to deploy them on powerful bespoke AI servers hosted on-premises or in the cloud. Why local LLM inference is desirable What if we could run state-of-the-art open-source LLMs on a typical personal computer? Wouldn’t we enjoy benefits like: Increased privacy: our data would    

With the recent advancements in augmented LLM capabilities, deployment of enterprise AI assistants (such as chatbots and agents) with access to internal databases is likely to increase; this trend could help with many tasks, from internal document summarization to personalized customer and employee support. However, data privacy of said databases can be a serious concern (see 1, 2 and 3) when deploying these models in production. So far, guardrails have emerged as the widely accepted technique to ensure the quality, […]