This technical blog post from Hugging Face introduces how combining n-gram language models (LMs) can significantly improve the performance of Wav2Vec2…
With the rise of open-source large language models, deploying these models in cloud environments in a secure, stable, and scalable manner has become a critical…
This blog post introduces the integration of Hugging Face's AutoNLP (now evolved into AutoTrain) with Prodigy, the popular data annotation tool developed by…
On December 21, 2021, the open-source machine learning world received major news: Gradio, the open-source library purpose-built for rapidly creating…
This article introduces DeepMind's Perceiver IO model and its integration into the Hugging Face Transformers library. Traditional Transformer models, while…
This classic Hugging Face blog post documents the birth of the "CodeParrot" project — an experiment in training a code generation model entirely from scratch…
Hugging Face announced the launch of its first custom virtual environment built on Unity ML-Agents: "Snowball Fight." This marks Hugging Face's formal…
This blog post introduces the fruits of a collaboration between Hugging Face and hardware chip design company Graphcore, showcasing how to use Hugging Face's…
In late 2021, Hugging Face launched the "Data Measurements Tool," an open-source, interactive utility designed to address the problem of "dataset black boxes"…
While GPUs dominate deep learning training today, a collaboration between Intel and Hugging Face demonstrates that through software and hardware optimization…
Automatic speech recognition (ASR) has achieved remarkable success for resource-rich languages such as English and standard Mandarin, but building…
This blog post is the second part of a technical guide co-authored by Hugging Face and Intel, designed to show developers how to push the inference performance…
In late 2021, the AI field witnessed an unprecedented explosive growth in large language models (LLMs). From OpenAI's GPT-3 at 175 billion parameters to the…
This announcement comes from the official Hugging Face blog, published in October 2021, celebrating the launch of the Hugging Face Course along with an…
This classic Hugging Face blog post (co-authored by Sentence-Transformers creator Nils Reimers and others) provides a detailed account of how to train…
This classic 2021 article from Hugging Face declared the official arrival of the "Machine Learning as Code" (ML as Code) era. The central argument is that…
This blog post from the Hugging Face community provides a detailed walkthrough of how to fine-tune OpenAI's CLIP (Contrastive Language-Image Pre-training)…
Hugging Face has officially launched its "Spaces" service with full support for the popular lightweight UI framework Gradio, aiming to make it easier for…
Hugging Face has announced the launch of its new "Spaces" feature, designed to provide the machine learning community with a simple, fast, and free platform…
The summer of 2021 was a vibrant and breakthrough season for Hugging Face. In this retrospective, Hugging Face summarizes the rich achievements produced over…
In September 2021, Hugging Face, the leading open-source AI community, and British AI chip design company Graphcore announced a strategic partnership aimed at…
Hugging Face has officially launched a new open-source toolkit called "Optimum" — an optimization and hardware acceleration library designed specifically for…
In the field of artificial intelligence, training large language models (LLMs) has always been an extremely resource-intensive task. Traditionally, this…
Hugging Face officially announced a deep integration with spaCy, the popular industrial-grade natural language processing (NLP) framework, formally bringing…
Hugging Face and Amazon Web Services (AWS) have entered into a deep collaboration aimed at simplifying the deployment process of machine learning models from…
Hugging Face officially announced a deep integration with the highly popular open-source library `sentence-transformers`. `sentence-transformers` (commonly…
In the field of natural language processing (NLP), the emergence of GPT-3 demonstrated the tremendous power of "Few-shot Learning" — where a model only needs…
In May 2021, Gradio officially released version 2.0 and announced a deep integration with the Hugging Face platform. This collaboration fundamentally changed…
In many real-world enterprise production environments, although GPUs offer extremely high throughput for deep learning inference, CPUs remain indispensable due…
Hugging Face has officially released a new open-source library called `Accelerate` — a lightweight helper library designed for PyTorch that aims to solve the…