AI BriefingHuggingFace Blog news
The latest AI and developer news from HuggingFace Blog, with short summaries.
Visit website →Hugging Face Launches SafeCoder
Hugging Face has launched SafeCoder, a self-hostable code assistant built for enterprise security.
Hugging Face Joins AWS Marketplace
Hugging Face Hub has joined AWS Marketplace, enabling unified billing through AWS accounts.
Deploying the DeepFloyd IF Model with BentoML
This explains how to efficiently deploy the DeepFloyd IF model, which has a multi-stage architecture, using BentoML.
🤗 Transformers Bark Optimization Guide
Covers how to optimize inference performance and memory efficiency of the Bark TTS model using Hugging Face's Optimum and Accelerate.
Guide to Fine-Tuning Llama 2 Using DPO
This explains how to efficiently fine-tune Llama 2 through the DPO method, which addresses the complexity of RLHF.
Deploying MusicGen with Inference Endpoints
This guide explains how to deploy the MusicGen model using Hugging Face's Inference Endpoints and a custom handler.
FHE-Based LLM Privacy Protection Technology
This introduces an LLM inference technology that uses Fully Homomorphic Encryption (FHE) to simultaneously protect user data and model IP.
Hugging Face automates dataset language detection with ML
Hugging Face automatically detects and updates language metadata for datasets using machine learning.
Segmind unveils lightweight SD models
Segmind has released SD-Small and SD-Tiny, lightweight Stable Diffusion models with reduced parameters achieved through knowledge distillation.
SDXL Core ML Support for Apple Silicon
Apple and Hugging Face have released Core ML optimization and quantization techniques to run SDXL efficiently on Mac.
Agents.js Library Released
HuggingFace has released Agents.js, a JavaScript library that grants LLMs tool-use capabilities in the browser and on servers.
Hugging Face Publishes Policy Recommendations on the EU AI Act
Hugging Face published five policy recommendations to ensure the EU AI Act does not hinder open-source ML development.
Hugging Face, Diffusers 1st Anniversary Achievements
Marking the first anniversary of its release, Hugging Face's Diffusers library summarized its major feature updates and development over the past year.
Meta Releases Llama 2 and Integrates with HF
Meta's open-source LLM Llama 2 has been released, and it is provided integrated with models and various tools through Hugging Face.
Overview of the Hugging Face Open Source LLM Ecosystem
A guide summarizing Hugging Face's open source LLM models, licenses, serving tools, and PEFT techniques.
Fine-Tuning Stable Diffusion on Intel CPU
This introduces a method for fine-tuning Stable Diffusion models by leveraging the AMX accelerator in Intel Sapphire Rapids CPUs.
Hugging Face Releases LLM Deployment Guide
It introduces how to deploy LLMs using Hugging Face's managed SaaS solution, Inference Endpoints, and its key features.
Building a Node.js-based LLM Web App Generator
This provides a technical guide for generating web apps from text using Node.js and the Hugging Face API.
Gaudi2 accelerates BridgeTower fine-tuning by 2.5x
Fine-tuning BridgeTower on Habana Gaudi2 achieved 2.5x faster performance compared to A100.
Causes and Challenges of Bias in Text-to-Image Models
This analyzes the causes of bias occurring in text-to-image (TTI) models and emphasizes the need for improved methodologies to evaluate it.