Community Blog & Articles

Community Articles

🏟️ Smol AI WorldCup: A 5-Axis Benchmark That Reveals What Small Language Models Can Really Do

NEO-unify: Building Native Multimodal Unified Models End to End

How NVIDIA AI-Q Reached \#1 on DeepResearch Bench I and II

MARL: Runtime Middleware That Reduces LLM Hallucination Without Fine-Tuning

Uncensor any LLM with abliteration

How NVIDIA Builds Open Data for AI

Structural Problems in AI Benchmarking and the Case for a Unified Evaluation Framework

Build an Agent That Thinks Like a Data Scientist: How We Hit #1 on DABStep with Reusable Tool Generation

Arabic TTS Arena: Ranking Voice Models the Way Chess Ranks Grandmasters

KV Caching Explained: Optimizing Transformer Inference Efficiency

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

The ML Engineer's Guide to Protein AI

Kanon 2 Reranker: the most powerful reranker for legal RAG

TiRex on the Edge

OpenMed: Six Months of Open-Source Medical AI and the Road Ahead

LLM based Audio models

Building Tucano 2: Open-Source Language Models That Actually _Think_ in Portuguese

ShopRLVE-GYM: Adaptive Verifiable Environments for E-Commerce Conversational Agents

Pruna 0.3.2: More OSS Algos, More Ways to Optimize

Code a simple RAG from scratch

cloudawspartnership

Introducing the Hugging Face LLM Inference Container for Amazon SageMaker

guideopen-source-collabcommunity

Introducing BERTopic Integration with the Hugging Face Hub

diffuserscpuintel

Optimizing Stable Diffusion for Intel CPUs with NNCF and 🤗 Optimum

+1

transformersquantizationbitsandbytes

Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA

+1

cloudazurepartnership

Hugging Face Collaborates with Microsoft to launch Hugging Face Model Catalog on Azure

cloudibmpartnership

Hugging Face and IBM partner on watsonx.ai, the next-generation enterprise studio for AI builders

pickleserializationload times

🐶Safetensors audited as really safe and becoming the default

diffusersdiffusioninstruction-tuning

Instruction-tuning Stable Diffusion with InstructPix2Pix

bigcodededuplication

Large-scale Near-deduplication Behind BigCode

llmnlpinference

Smaller is better: Q8-Chat, an efficient generative AI experience on Xeon

Hugging Face Selected for the French Data Protection Agency Enhanced Support Program

Run a Chatgpt-like Chatbot on a Single GPU with ROCm

nlpcommunityresearch

Introducing RWKV - An RNN with the advantages of a transformer

Assisted Generation: a new direction toward low-latency text generation

Community Articles

NEW Articles from Team or Enterprise organizations will get promoted to the main section.

🏟️ Smol AI WorldCup: A 5-Axis Benchmark That Reveals What Small Language Models Can Really Do

NEO-unify: Building Native Multimodal Unified Models End to End

How NVIDIA AI-Q Reached \#1 on DeepResearch Bench I and II

MARL: Runtime Middleware That Reduces LLM Hallucination Without Fine-Tuning

Uncensor any LLM with abliteration

How NVIDIA Builds Open Data for AI

Structural Problems in AI Benchmarking and the Case for a Unified Evaluation Framework

Build an Agent That Thinks Like a Data Scientist: How We Hit #1 on DABStep with Reusable Tool Generation

Arabic TTS Arena: Ranking Voice Models the Way Chess Ranks Grandmasters

KV Caching Explained: Optimizing Transformer Inference Efficiency

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

The ML Engineer's Guide to Protein AI

Kanon 2 Reranker: the most powerful reranker for legal RAG

TiRex on the Edge

OpenMed: Six Months of Open-Source Medical AI and the Road Ahead

LLM based Audio models

Building Tucano 2: Open-Source Language Models That Actually _Think_ in Portuguese

ShopRLVE-GYM: Adaptive Verifiable Environments for E-Commerce Conversational Agents

Pruna 0.3.2: More OSS Algos, More Ways to Optimize

Code a simple RAG from scratch

View all articles