Hugging Face Blog

huggingface.co · EN

The Hugging Face blog

Latest posts

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

    · huggingface.co
  2. How to Use NVIDIA Warp and MjWarp to Accelerate Robotics Simulation and Learning Workflows

    · huggingface.co
  3. How UK AISI and EvalEval Are Making Benchmark Results Reproducible

    · huggingface.co
  4. Transformers now runs llama.cpp quants

    · huggingface.co
  5. Jun Kim, oMLX creator and maintainer, joins Hugging Face to support the MLX community

    · huggingface.co
  6. Pruning LLMs Like a Physicist: Block Removal as an Ising Optimization Problem

    · huggingface.co
  7. tokenizers v1: encode, decode and scaling, measured

    · huggingface.co
  8. Your Agent Aced the Task. Will It Do It Again?

    · huggingface.co
  9. Async GRPO with LoRA across HF Jobs: a bucket, a proxy, and no NCCL

    · huggingface.co
  10. Rebuilding AUTOMATIC1111 with Gradio Workflow

    · huggingface.co
  11. NeoMME: an efficient Multimodal-native and Multilingual Encoder

    · huggingface.co
  12. Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps

    · huggingface.co
  13. Give Your Coding Agents a Memory You Own

    · huggingface.co
  14. Training a coding model to paint watercolours with TRL and OpenEnv

    · huggingface.co
  15. BenchMIRT: What are LLM benchmarks actually measuring?

    · huggingface.co
  16. Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI

    · huggingface.co
  17. The Open ASR Leaderboard Adds Its First Global South Language

    · huggingface.co
  18. Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers

    · huggingface.co
  19. Granite 4.2 LLMs: How They're Built

    · huggingface.co
  20. Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original

    · huggingface.co

In the directory since 25 Sept 2026 · last checked 25 Sept 2026 · RSS

Report a problem with this feed