Blog, Articles, and discussions

Community Articles

ViDoRe V3: a comprehensive evaluation of retrieval for enterprise use-cases

and 4 others •

The 1 Billion Token Challenge: Finding the Perfect Pre-training Mix

Why Did MiniMax M2 End Up as a Full Attention Model?

Granite 4.0 Nano: Just how small can you go?

and 1 other •

⚡ Power, Heat, and Intelligence ☁️ - AI Data Centers Explained 🏭

and 1 other •

Running Large Transformer Models on Mobile and Edge Devices

Llasa Goes RL: Training LLaSA with GRPO for Improved Prosody and Expressiveness

On the Shifting Global Compute Landscape

and 1 other •

What makes good reasoning data

Evaluate Your Own RAG: Why Best Practices Failed Us

and 4 others •

KV Caching Explained: Optimizing Transformer Inference Efficiency

Ultra-Long Sequence Parallelism: Ulysses + Ring-Attention Technical Principles and Implementation

Classement compar:IA : des votes des utilisateurs au classement participatif des modèles

Budget Alignment: Making Models Reason in the User’s Language

and 2 others •

Small Language Models (SLM): A Comprehensive Overview

From GRPO to DAPO and GSPO: What, Why, and How

Aligning to What? Rethinking Agent Generalization in MiniMax M2

Introduction to State Space Models (SSM)

Let's talk about LLM evaluation

Code a simple RAG from scratch

qwenchat-templatellms

The 4 Things Qwen-3’s Chat Template Teaches Us

Welcoming Llama Guard 4 on Hugging Face Hub

llmsinferencequantization

Introducing AutoRound: Intel’s Advanced Quantization for LLMs and VLMs

+5

agentshubinference

Tiny Agents: an MCP-powered agent in 50 lines of code

gradioui-frameworkpython

17 Reasons Why Gradio Isn't Just Another UI Library

llmsinference-providerscohere

Cohere on Hugging Face Inference Providers 🔥

+3

long-contextbenchmarknlp

Introducing HELMET: Holistically Evaluating Long-context Language Models

+3

roboticsacquisitionannouncement

Hugging Face to sell open-source robots thanks to Pollen Robotics acquisition 🤖

hubpartnershipssecurity

4M Models Scanned: Protect AI + Hugging Face 6 Months In

real-timeaudiovideo

Hugging Face and Cloudflare Partner to Make Real-Time Speech and Video Seamless with FastRTC

leaderboardevaluationnlp

Arabic Leaderboards: Introducing Arabic Instruction Following, Updating AraGen, and More

+2

Welcome Llama 4 Maverick & Scout on Hugging Face

+3

gradioopen-sourcecommunity

Journey to 1 Million Gradio Users!

educationnlp-coursellm-course

The NLP Course is becoming the LLM Course

+6

Community Articles

ViDoRe V3: a comprehensive evaluation of retrieval for enterprise use-cases

and 4 others •

The 1 Billion Token Challenge: Finding the Perfect Pre-training Mix

Why Did MiniMax M2 End Up as a Full Attention Model?

Granite 4.0 Nano: Just how small can you go?

and 1 other •

⚡ Power, Heat, and Intelligence ☁️ - AI Data Centers Explained 🏭

and 1 other •

Running Large Transformer Models on Mobile and Edge Devices

Llasa Goes RL: Training LLaSA with GRPO for Improved Prosody and Expressiveness

On the Shifting Global Compute Landscape

and 1 other •

What makes good reasoning data

Evaluate Your Own RAG: Why Best Practices Failed Us

and 4 others •

KV Caching Explained: Optimizing Transformer Inference Efficiency

Ultra-Long Sequence Parallelism: Ulysses + Ring-Attention Technical Principles and Implementation

Classement compar:IA : des votes des utilisateurs au classement participatif des modèles

Budget Alignment: Making Models Reason in the User’s Language

and 2 others •

Small Language Models (SLM): A Comprehensive Overview

From GRPO to DAPO and GSPO: What, Why, and How

Aligning to What? Rethinking Agent Generalization in MiniMax M2

Introduction to State Space Models (SSM)

Let's talk about LLM evaluation

Code a simple RAG from scratch

View all