Hacker News with Generative AI: Hugging Face

On-device small language models with multimodality, RAG, and Function Calling (googleblog.com)
Last year Google AI Edge introduced support for on-device small language models (SLMs) with four initial models on Android, iOS, and Web. Today, we are excited to expand support to over a dozen models including the new Gemma 3 and Gemma 3n models, hosted on our new LiteRT Hugging Face community.

Mobile Development, Artificial Intelligence, Google, Hugging Face

14 points by cuuupid 3 days ago | 1 comments

Vector Search with DuckDB (huggingface.co)
Datasets on the Hugging Face Hub rely on parquet files. We can interact with these files using DuckDB as a fast in-memory database system. One of DuckDB’s features is vector similarity search which can be used with or without an index.

Databases, Vector Search, Hugging Face, DuckDB

17 points by alexmolas 86 days ago | 0 comments

Train faster static embedding models with sentence transformers (huggingface.co)
This blog post introduces a method to train static embedding models that run 100x to 400x faster on CPU than state-of-the-art embedding models, while retaining most of the quality. This unlocks a lot of exciting use cases, including on-device and in-browser execution, edge computing, low power and embedded applications.

Machine Learning, Sentence Embeddings, Performance Optimization, Hugging Face

52 points by stephantul 128 days ago | 1 comments

Spaces ZeroGPU: Dynamic GPU Allocation for Spaces (huggingface.co)

GPU Allocation, Machine Learning, Cloud Computing, Hugging Face

9 points by 9woc 159 days ago | 1 comments

Improving Parquet Dedupe on Hugging Face Hub (huggingface.co)
The Xet team at Hugging Face is working on improving the efficiency of the Hub's storage architecture to make it easier and quicker for users to store and update data and models.

Data Storage, Machine Learning, Hugging Face, Efficiency

47 points by ylow 227 days ago | 17 comments

Exponential growth brews 1M AI models on Hugging Face (arstechnica.com)
On Thursday, AI hosting platform Hugging Face surpassed 1 million AI model listings for the first time, marking a milestone in the rapidly expanding field of machine learning.

Artificial Intelligence, Machine Learning, Hugging Face

8 points by danieldk 237 days ago | 0 comments

Hugging Face replacing Git LFS storage back end (xethub.com)

Hugging Face, Git LFS, Software Development, Version Control

11 points by erinys 276 days ago | 5 comments

DevRel at HuggingFace (dx.tips)

DevRel, Hugging Face, Artificial Intelligence, Machine Learning

151 points by swyx 311 days ago | 86 comments

Join Super AI Agent Hackathon at Stanford, Hosted by HuggingFace and Nexa AI (twitter.com)