This is a beginner's guide written by the official Hugging Face blog for "total noobs" with absolutely no machine learning background, aimed at demystifying…
This technical blog post from Hugging Face details how to locally deploy and run Microsoft's lightweight Phi-2 language model (2.7 billion parameters) on a…
As the parameter counts of large language models (LLMs) have skyrocketed, the hardware requirements for training and fine-tuning these models have risen…
Hugging Face has announced a deep partnership with NVIDIA to directly integrate NVIDIA DGX Cloud services into the Hugging Face platform. This collaboration…
Hugging Face has officially introduced Quanto, a brand-new quantization library designed for PyTorch, which has been integrated as a backend into the Hugging…
The Hugging Face official blog has published a post introducing WebSight, a brand-new open-source dataset designed to address the bottleneck that multimodal…
When building Retrieval-Augmented Generation (RAG) systems, converting large volumes of text into embeddings (vectors) is an indispensable and computationally…
Hugging Face has announced the launch of a new multimodal benchmark and leaderboard called "ConTextual," aimed at addressing the shortcomings of existing…
### Background and Challenge: The High-Quality Data Bottleneck In the current development of generative AI and large language models (LLMs), the industry…
With the explosive growth of large language models (LLMs), the demand for high-performance, cost-effective AI hardware has increased significantly. Intel Gaudi…
The BigCode community, jointly led by Hugging Face and ServiceNow, together with NVIDIA, has officially announced the launch of a new generation of open-source…
This guide from Hugging Face systematically introduces the technical principles, categories, existing tools, and real-world challenges of AI watermarking. As…
This article provides an in-depth introduction to Matryoshka Representation Learning (MRL), also known as Matryoshka embedding models. Traditional embedding…
After Google released the Gemma family of open-source models (including 2B and 7B parameter versions), Hugging Face promptly published this practical…
### Background: The Shortcomings of Static Safety Evaluations As large language models (LLMs) are widely adopted across industries, AI safety has become an…
Google has officially released a new family of open-source large language models called "Gemma" — a series of lightweight, state-of-the-art open-source models…
Hugging Face and South Korea's leading AI startup Upstage have jointly announced the launch of the "Open Ko-LLM Leaderboard." This is a brand-new evaluation…
Hugging Face's PEFT (Parameter-Efficient Fine-Tuning) library has recently received a major update, officially adding support for several advanced adapter…
This article takes an in-depth look at the critical role of "synthetic data" in the open-source ecosystem, and explains how it helps enterprises and developers…
AMD and Hugging Face have jointly announced the "AMD Pervasive AI Developer Contest," a global competition designed to inspire developers worldwide to build…
Hugging Face has announced official support for an OpenAI-compatible Messages API (i.e., the `/v1/chat/completions` endpoint) in its high-performance…
In the large language model (LLM) space, the Mixture of Experts (MoE) architecture (as seen in models like Mixtral 8x7B) has proven capable of dramatically…
Hugging Face has announced the launch of the new **NPHardEval** leaderboard — a benchmark specifically designed to evaluate the reasoning capabilities of large…
This blog post from Hugging Face provides an in-depth exploration of how to implement "Constitutional AI (CAI)" using open-source large language models (Open…
Hugging Face has partnered with AWS to officially bring its widely popular open-source LLM inference optimization framework, Text Generation Inference (TGI)…
Hugging Face has partnered with Patronus AI — a startup focused on LLM evaluation and defense — to officially launch the **Enterprise Scenarios Leaderboard**…
While large language models (LLMs) have demonstrated remarkable generative capabilities across many domains, "hallucination" — where a model confidently…
### Introduction: Capability Is Not Safety — A New Benchmark for LLM Safety Evaluation As large language models (LLMs) are adopted more deeply across…
Hugging Face and Google officially announced a landmark strategic partnership at the end of January 2024. The core objective of this collaboration is to deeply…
This official Hugging Face blog post provides a detailed guide on how to use open-source large language models (LLMs) as intelligent agents within LangChain…