Reader

Hugging Face - Blog

• 17 Reasons Why Gradio Isn't Just Another UI Library
• Cohere on Hugging Face Inference Providers 🔥
• Introducing HELMET
• Hugging Face to sell open-source robots thanks to Pollen Robotics acquisition 🤖
• 4M Models Scanned: Protect AI + Hugging Face 6 Months In
• Hugging Face and Cloudflare Partner to Make Real-Time Speech and Video Seamless with FastRTC
• Arabic Leaderboards: Introducing Arabic Instruction Following, Updating AraGen, and More
• Welcome Llama 4 Maverick & Scout on Hugging Face!
• Journey to 1 Million Gradio Users!
• The NLP Course is becoming the LLM Course!
• How Hugging Face Scaled Secrets Management for AI Infrastructure
• Accelerating LLM Inference with TGI on Intel Gaudi
• Training and Finetuning Reranker Models with Sentence Transformers v4
• Introducing Gradio's new Dataframe!
• The New and Fresh analytics in Inference Endpoints
• Open R1: How to use OlympicCoder locally for coding?
• AI Policy: 🤗 Response to the White House AI Action Plan RFI
• NVIDIA's GTC 2025 Announcement for Physical AI Developers: New Open Models and Datasets
• Xet is on the Hub
• Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM
• LeRobot goes to driving school: World’s largest open-source self-driving dataset
• LLM Inference on Edge: A Fun and Easy Guide to run LLMs via React Native on your Phone!
• A Deepdive into Aya Vision: Advancing the Frontier of Multilingual Multimodality
• Hugging Face and JFrog partner to make AI Security more transparent
• Trace & Evaluate your Agent with Arize Phoenix
• FastRTC: The Real-Time Communication Library for Python
• HuggingFace, IISc partner to supercharge model building on India's diverse languages
• Remote VAEs for decoding with HF endpoints 🤗
• SigLIP 2: A better multilingual vision language encoder
• SmolVLM2: Bringing Video Understanding to Every Device
• Introducing Three New Serverless Inference Providers: Hyperbolic, Nebius AI Studio, and Novita 🔥
• Welcome Fireworks.ai on the Hub 🎆
• Fixing Open LLM Leaderboard with Math-Verify
• 1 Billion Classifications
• From Chunks to Blocks: Accelerating Uploads and Downloads on the Hub
• Build awesome datasets for video generation
• The Open Arabic LLM Leaderboard 2
• Open-source DeepResearch – Freeing our search agents
• π0 and π0-FAST: Vision-Language-Action Models for General Robot Control
• DABStep: Data Agent Benchmark for Multi-step Reasoning
• The AI tools for Art Newsletter - Issue 1
• How to deploy and fine-tune DeepSeek models on AWS
• Welcome to Inference Providers on the Hub 🔥
• Open-R1: a fully open reproduction of DeepSeek-R1
• State of open video generation models in Diffusers
• We now support VLMs in smolagents!
• SmolVLM Grows Smaller – Introducing the 250M & 500M Models!
• Hugging Face and FriendliAI partner to supercharge model deployment on the Hub
• Timm ❤️ Transformers: Use any timm model with transformers
• Introducing multi-backends (TRT-LLM, vLLM) support for Text Generation Inference
• Train 400x faster Static Embedding Models with Sentence Transformers
• AI Agents Are Here. What Now?
• Visual Document Retrieval Goes Multilingual
• CO₂ Emissions and Models Performance: Insights from the Open LLM Leaderboard
• Introducing smolagents: simple agents that write actions in code.
• Visualize and understand GPU memory in PyTorch
• Controlling Language Model Generation with NVIDIA's LogitsProcessorZoo
• Evaluating Audio Reasoning with Big Bench Audio
• Finally, a Replacement for BERT: Introducing ModernBERT
• Bamba: Inference-Efficient Hybrid Mamba2 Model
• Welcome the Falcon 3 Family of Open Models!
• Benchmarking Language Model Performance on 5th Gen Xeon at GCP
• Introducing the Synthetic Data Generator - Build Datasets with Natural Language
• LeMaterial: an open source initiative to accelerate materials discovery and research
• Hugging Face models in Amazon Bedrock
• Open Preference Dataset for Text-to-Image Generation by the 🤗 Community
• “How good are LLMs at fixing their mistakes? A chatbot arena experiment with Keras and TPUs
• Welcome PaliGemma 2 – New vision language models by Google
• Rethinking LLM Evaluation with 3C3H: AraGen Benchmark and Leaderboard
• Investing in Performance: Fine-tune small models with LLM insights - a CFM case study
• Open Source Developers Guide to the EU AI Act
• Rearchitecting Hugging Face Uploads and Downloads
• SmolVLM - small yet mighty Vision Language Model
• You could have designed state of the art positional encoding
• Letting Large Models Debate: The First Multilingual LLM Debate Competition
• From Files to Chunks: Improving Hugging Face Storage Efficiency
• Faster Text Generation with Self-Speculative Decoding
• Introduction to the Open Leaderboard for Japanese LLMs
• Judge Arena: Benchmarking LLMs as Evaluators
• Hugging Face + PyCharm
• Argilla 2.4: Easily Build Fine-Tuning and Evaluation datasets on the Hub — No Code Required
• Universal Assisted Generation: Faster Decoding with Any Assistant Model
• Expert Support case study: Bolstering a RAG app with LLM-as-a-Judge
• A Deepdive into Aya Expanse: Advancing the Frontier of Multilinguality
• Introducing SynthID Text
• Introducing HUGS - Scale your AI with Open Models
• CinePile 2.0 - making stronger datasets with adversarial refinement
• Hugging Face Teams Up with Protect AI: Enhancing Model Security for the Community
• Transformers.js v3: WebGPU support, new models & tasks, and more…
• 🧨 Diffusers welcomes Stable Diffusion 3.5 Large
• Releasing Outlines-core 0.1.0: structured generation in Rust and Python
• Deploying Speech-to-Speech on Hugging Face
• Llama 3.2 in Keras
• Fixing Gradient Accumulation
• Introducing the AMD 5th Gen EPYC™ CPU
• A Security Review of Gradio 5
• Welcome, Gradio 5
• Scaling AI-based Data Processing with Hugging Face + Dask
• Faster Assisted Generation with Dynamic Speculation
• Improving Parquet Dedupe on Hugging Face Hub