Open Source & Tools

Holo4: powering generalist computer-use agents

Welcome RL Environments to the hub

Accelerating vision-language models with LFM2.5-VL-DSpark

Jun Kim, oMLX creator and maintainer, joins Hugging Face to support the MLX community

Transformers now runs llama.cpp quants

How UK AISI and EvalEval Are Making Benchmark Results Reproducible

tokenizers v1: encode, decode and scaling, measured

AI-generated posters don’t have to be horrible

1902 points on Hacker News

Your Agent Aced the Task. Will It Do It Again?

Rebuilding AUTOMATIC1111 with Gradio Workflow

Async GRPO with LoRA across HF Jobs: a bucket, a proxy, and no NCCL

NeoMME: an efficient Multimodal-native and Multilingual Encoder

Training a coding model to paint watercolours with TRL and OpenEnv

Give Your Coding Agents a Memory You Own

Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps

BenchMIRT: What are LLM benchmarks actually measuring?

Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI

The Open ASR Leaderboard Adds Its First Global South Language

Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers

Granite 4.2 LLMs: How They're Built