Hugging Face's logo

Blog, Articles, and discussions

Faster Text Generation with Self-Speculative Decoding

By  ariG23498 November 20, 2024 • 16

Community Articles
view all

Introduction to the Open Leaderboard for Japanese LLMs

By  akimfromparis November 20, 2024 guest • 11

Universal Assisted Generation: Faster Decoding with Any Assistant Model

By  danielkorat October 29, 2024 guest • 47

Scaling AI-based Data Processing with Hugging Face + Dask

By  scj13 October 9, 2024 • 23

Faster Assisted Generation with Dynamic Speculation

By  jmamou October 8, 2024 guest • 34

🇨🇿 BenCzechMark - Can your LLM Understand Czech?

By  mfajcik October 1, 2024 • 16

Llama can now see and run on your device - welcome Llama 3.2

By  merve September 25, 2024 • 169

Fine-tuning LLMs to 1.58bit: extreme quantization made easy

By  medmekk September 18, 2024 • 202

The 5 Most Under-Rated Tools on Hugging Face

By  derek-thomas August 22, 2024 • 85

Deploy Meta Llama 3.1 405B on Google Cloud Vertex AI

By  alvarobartt August 19, 2024 • 18

Welcome FalconMamba: The first strong attention-free 7B model

By  JingweiZuo August 12, 2024 guest • 102

Tool Use, Unified

By  rocketknight1 August 12, 2024 • 64

Google releases Gemma 2 2B, ShieldGemma and Gemma Scope

By  Xenova July 31, 2024 • 59

Llama 3.1 - 405B, 70B & 8B with multilinguality and long context

By  philschmid July 23, 2024 • 215

TGI Multi-LoRA: Deploy Once, Serve 30 Models

By  derek-thomas July 18, 2024 • 48