Blog, Articles, and discussions

Community Articles

AI for Food Allergies

and 3 others •

Introducing MTEB v2: Evaluation of embedding and retrieval systems for more than just text

and 2 others •

Announcing Hugging Face Fundamentals: A New Learning Track on DataCamp

Introducing the Massive Legal Embedding Benchmark (MLEB)

and 1 other •

How I Built Lightning-Fast Vector Search for Legal Documents

Art of Focus: Page-Aware Sparse Attention and Ling 2.0’s Quest for Efficient Context Length Scaling

and 19 others •

Scaling Test-Time Compute to Achieve Gold Medal at IOI 2025 with Open-Weight Models

and 3 others •

GSMA Open-Telco LLM Benchmarks 2.0: The first dedicated LLM Evaluation for Telecoms

and 15 others •

There is no such thing as a tokenizer-free lunch

How Financial News Can Be Used to Train Good Financial Models

Code a simple RAG from scratch

Visualizing How VLMs Work

and 1 other •

Model statistics of the 50 most downloaded entities on Hugging Face

Introduction to State Space Models (SSM)

Understanding Vector Quantization in VQ-VAE

Small Language Models (SLM): A Comprehensive Overview

mem-agent: Equipping LLM Agents with Memory Using RL

and 1 other •

Granite Embedding R2: Setting New Standards for Enterprise Retrieval

Llama‑Embed‑Nemotron‑8B Text Embedding Model Ranks First on Multilingual MTEB Leaderboard

and 4 others •

about 18 hours ago

Uncensor any LLM with abliteration

roboticsaidatasets

NVIDIA's GTC 2025 Announcement for Physical AI Developers: New Open Models and Datasets

+1

Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM

roboticsaicommunity

LeRobot goes to driving school: World’s largest open-source self-driving dataset

communityhubllms

LLM Inference on Edge: A Fun and Easy Guide to run LLMs via React Native on your Phone!

multimodalvisionvlm

A Deepdive into Aya Vision: Advancing the Frontier of Multilingual Multimodality

hubpartnershipssecurity

Hugging Face and JFrog partner to make AI Security more transparent

phoenixagentssmolagents

Trace & Evaluate your Agent with Arize Phoenix

February 28, 2025

open-source-collabaudiocommunity

HuggingFace, IISc partner to supercharge model building on India's diverse languages

February 27, 2025

real-timeaudiovideo

FastRTC: The Real-Time Communication Library for Python

February 25, 2025

diffusersvaeinference endpoints

Remote VAEs for decoding with HF endpoints 🤗

February 24, 2025

multimodalvision

SigLIP 2: A better multilingual vision language encoder

February 21, 2025

vlmmultimodalvideo

SmolVLM2: Bringing Video Understanding to Every Device

+2

February 20, 2025

multimodalLLMvision

PaliGemma 2 Mix - New Instruction Vision Language Models by Google

February 19, 2025

announcementhubinference-providers

Introducing Three New Serverless Inference Providers: Hyperbolic, Nebius AI Studio, and Novita 🔥

+3

February 18, 2025

Community Articles

AI for Food Allergies

and 3 others •

Introducing MTEB v2: Evaluation of embedding and retrieval systems for more than just text

and 2 others •

Announcing Hugging Face Fundamentals: A New Learning Track on DataCamp

Introducing the Massive Legal Embedding Benchmark (MLEB)

and 1 other •

How I Built Lightning-Fast Vector Search for Legal Documents

Art of Focus: Page-Aware Sparse Attention and Ling 2.0’s Quest for Efficient Context Length Scaling

and 19 others •

Scaling Test-Time Compute to Achieve Gold Medal at IOI 2025 with Open-Weight Models

and 3 others •

GSMA Open-Telco LLM Benchmarks 2.0: The first dedicated LLM Evaluation for Telecoms

and 15 others •

There is no such thing as a tokenizer-free lunch

How Financial News Can Be Used to Train Good Financial Models

Code a simple RAG from scratch

Visualizing How VLMs Work

and 1 other •

Model statistics of the 50 most downloaded entities on Hugging Face

Introduction to State Space Models (SSM)

Understanding Vector Quantization in VQ-VAE

Small Language Models (SLM): A Comprehensive Overview

mem-agent: Equipping LLM Agents with Memory Using RL

and 1 other •

Granite Embedding R2: Setting New Standards for Enterprise Retrieval

Llama‑Embed‑Nemotron‑8B Text Embedding Model Ranks First on Multilingual MTEB Leaderboard

and 4 others •

about 18 hours ago

Uncensor any LLM with abliteration

View all