Blog, Articles, and discussions

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

Community Articles

Training and Finetuning Reranker Models with Sentence Transformers v4

By March 26, 2025 • 107

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

By March 12, 2025 • 384

SmolVLM2: Bringing Video Understanding to Every Device

By February 20, 2025 guest • 230

1 Billion Classifications

By February 13, 2025 guest • 43

The Open Arabic LLM Leaderboard 2

By February 10, 2025 guest • 30

Train 400x faster Static Embedding Models with Sentence Transformers

By January 15, 2025 • 170

Visual Document Retrieval Goes Multilingual

By January 10, 2025 guest • 70

Introducing smolagents: simple agents that write actions in code.

By December 31, 2024 • 968

Finally, a Replacement for BERT: Introducing ModernBERT

By December 19, 2024 guest • 605

Bamba: Inference-Efficient Hybrid Mamba2 Model

By December 18, 2024 guest • 51

Welcome the Falcon 3 Family of Open Models!

By December 17, 2024 • 125

Rethinking LLM Evaluation with 3C3H: AraGen Benchmark and Leaderboard

SmolVLM - small yet mighty Vision Language Model

By November 26, 2024 • 233

Letting Large Models Debate: The First Multilingual LLM Debate Competition

By November 20, 2024 guest • 30

Blog, Articles, and discussions

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

🦸🏻#14: What Is MCP, and Why Is Everyone – Suddenly!– Talking About It?

Are AI Agents Sustainable? It depends

Comparing sub 50GB Llama 4 Scout quants (KLD/Top P)

Deepsite：HuggingFace Founder Introduces Free Web-Based 'Cursor' Alternative

ChatGPT-4o's Image Generation Capabilities and Its Wild Examples

Reasoning Datasets Competition

Topic 33: Slim Attention, KArAt, XAttention and Multi-Token Attention Explained – What’s Really Changing in Transformers?

Empowering Public Organizations: Preparing Your Data for the AI Era

Model2Vec: Distill a Small Fast Model from any Sentence Transformer

DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge

Open-Source Handwritten Signature Detection Model

Code a simple RAG from scratch

Why AI Companion Applications are a Lifeline, Not a Threat

The Large Language Model Course

Manus AI: The Best Autonomous AI Agent Redefining Automation and Productivity

Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth

Decoding Strategies in Large Language Models

GSMA Open-Telco LLM Benchmarks

Open R1: Update #3

KV Caching Explained: Optimizing Transformer Inference Efficiency