Hugging Face's logo

Blog, Articles, and discussions

Universal Assisted Generation: Faster Decoding with Any Assistant Model

By  danielkorat October 29, 2024 guest • 42

Community Articles
view all

From OpenAI to Open LLMs with Messages API

By  andrewrreed February 8, 2024 • 12

Accelerate StarCoder with 🤗 Optimum Intel on Xeon: Q8/Q4 and Speculative Decoding

By  ofirzaf January 30, 2024 guest • 4

Open-source LLMs as LangChain Agents

By  m-ric January 24, 2024 • 35

Preference Tuning LLMs with Direct Preference Optimization Methods

By  kashif January 18, 2024 • 35

2023, year of open LLMs

By  clefourrier December 18, 2023 • 5

Welcome Mixtral - a SOTA Mixture of Experts on Hugging Face

By  lewtun December 11, 2023 • 11

Mixture of Experts Explained

By  osanseviero December 11, 2023 • 187

SetFitABSA: Few-Shot Aspect Based Sentiment Analysis using SetFit

By  ronenlap December 6, 2023 guest • 6

Open LLM Leaderboard: DROP deep dive

By  clefourrier December 1, 2023 • 4

Introducing Prodigy-HF: a direct integration with Hugging Face

By  koaning November 7, 2023 • 1

Comparing the Performance of LLMs: A Deep Dive into Roberta, Llama 2, and Mistral for Disaster Tweets Analysis with Lora

By  mehdiiraqui November 7, 2023 • 4

Personal Copilot: Train Your Own Coding Assistant

By  smangrul October 27, 2023 • 30

Chat Templates: An End to the Silent Performance Killer

By  rocketknight1 October 3, 2023 • 13

Non-engineers guide: Train a LLaMA 2 chatbot

By  2legit2overfit September 28, 2023 • 1