Community Blog & Articles

Community Articles

MosaicLeaks: Can your research agent keep a secret?

Beyond LoRA: Can you beat the most popular fine-tuning technique?

Is it agentic enough? Benchmarking open models on your own tooling

MolmoMotion: Language-guided 3D motion forecasting

From the Hugging Face Hub to robot hardware with Strands Agents and LeRobot

GLM-5.2: Built for Long-Horizon Tasks

Agentic Resource Discovery: Let agents search

Profiling in PyTorch (Part 2): From nn.Linear to a Fused MLP

How an Agent Built a 3D Paris Gallery by Chaining Two Hugging Face Spaces

Migrating Your GitHub CI to Hugging Face Jobs

The Open Source Community is backing OpenEnv for Agentic RL

Nemotron 3.5 Content Safety: Customizable Multimodal Safety for Global Enterprise AI

Designing the hf CLI as an agent-optimized way to work with the Hub

Direct Preference Optimization Beyond Chatbots

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

Community Blog & Articles

Party is over: regularizing ColBERT models to fix efficient ANN methods

FINAL-Bench Quantum: An Open, Neutral Benchmark for Quantum-Computing Methods

Introducing North Mini Code: Cohere’s First Model For Developers

olmo-eval: An evaluation workbench for the model development loop

PitchFight AI: Practice the Pitch Before the Real Room

Intel XPU Kernel Skill: LLM-driven Triton kernel optimization for the Hugging Face Kernel Hub

Eyas: AI Security Camera Agent

QLORA SFT Distillation Effects on Qwen3.6 27B Agentic Coding Harness Fluency

The Office Meets Silicon Valley

KV Caching Explained: Optimizing Transformer Inference Efficiency

How to Fine-Tune Nemotron 3.5 ASR for Your Language, Domain, or Accent

Introducing Serge: GitHub-Native AI Code Review

Building an AI Interview Coach for the BuildSmall Hackathon 2026

Code a simple RAG from scratch

Welcome NVIDIA Cosmos 3: The First Open Omni-model for Physical AI Reasoning and Action

Fine-tune FLUX.2 [klein] with a LoRA under 60 minutes

Lolaby — AI-powered lullabies

Closet Twin: Your AI-Powered Personal Stylist Built for the Build Small Hackathon

How We Built OpenMythos: A Cybersecurity LLM Trained from Scratch

I fine-tuned a model for free from one prompt, with TRL and the Google Colab CLI

MosaicLeaks: Can your research agent keep a secret?

Beyond LoRA: Can you beat the most popular fine-tuning technique?

Is it agentic enough? Benchmarking open models on your own tooling

MolmoMotion: Language-guided 3D motion forecasting

From the Hugging Face Hub to robot hardware with Strands Agents and LeRobot

GLM-5.2: Built for Long-Horizon Tasks

Agentic Resource Discovery: Let agents search

Profiling in PyTorch (Part 2): From nn.Linear to a Fused MLP

How an Agent Built a 3D Paris Gallery by Chaining Two Hugging Face Spaces

Migrating Your GitHub CI to Hugging Face Jobs

The Open Source Community is backing OpenEnv for Agentic RL

Nemotron 3.5 Content Safety: Customizable Multimodal Safety for Global Enterprise AI

Designing the hf CLI as an agent-optimized way to work with the Hub

Direct Preference Optimization Beyond Chatbots

Party is over: regularizing ColBERT models to fix efficient ANN methods

FINAL-Bench Quantum: An Open, Neutral Benchmark for Quantum-Computing Methods

Introducing North Mini Code: Cohere’s First Model For Developers

olmo-eval: An evaluation workbench for the model development loop

PitchFight AI: Practice the Pitch Before the Real Room

Intel XPU Kernel Skill: LLM-driven Triton kernel optimization for the Hugging Face Kernel Hub

Eyas: AI Security Camera Agent

QLORA SFT Distillation Effects on Qwen3.6 27B Agentic Coding Harness Fluency

The Office Meets Silicon Valley

KV Caching Explained: Optimizing Transformer Inference Efficiency

How to Fine-Tune Nemotron 3.5 ASR for Your Language, Domain, or Accent

Introducing Serge: GitHub-Native AI Code Review

Building an AI Interview Coach for the BuildSmall Hackathon 2026

Code a simple RAG from scratch

Welcome NVIDIA Cosmos 3: The First Open Omni-model for Physical AI Reasoning and Action

Fine-tune FLUX.2 [klein] with a LoRA under 60 minutes

Lolaby — AI-powered lullabies

Closet Twin: Your AI-Powered Personal Stylist Built for the Build Small Hackathon

How We Built OpenMythos: A Cybersecurity LLM Trained from Scratch

I fine-tuned a model for free from one prompt, with TRL and the Google Colab CLI