Training a coding model to paint watercolours with TRL and OpenEnv
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Hugging Face Blog20 min read
hugging face
55 stories
Give Your Coding Agents a Memory You Own
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Hugging Face Blog8 min read
Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Hugging Face Blog9 min read
BenchMIRT: What are LLM benchmarks actually measuring?
📄 Tech Report: http://allenai.org/papers/benchmirt | 📊 Data: https://huggingface.co/collections/allenai/benchmirt | 💻 Code: https://github.com/allenai/BenchMIRT
Hugging Face Blog7 min read
Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Hugging Face Blog9 min read
The Open ASR Leaderboard Adds Its First Global South Language
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Hugging Face Blog13 min read
Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Hugging Face Blog27 min read
Granite 4.2 LLMs: How They're Built
TL;DR: Granite 4.2 is our first family of dense, decoder-only reasoning LLMs, released in three sizes: 3B, 8B, and 30B. These models are post-trained from Granite-4.1 base models.
Hugging Face Blog21 min read
Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original
Our latest paper, Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs, asks a question that the field has mostly left open: once a model has already been through structural compression, not just quantization, how well does that recovery step actually work, and what…
Hugging Face Blog11 min read
Wire It, Run It, Deploy It: AI Workflows in Gradio
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Hugging Face Blog5 min read
How Hugging Face Inference Endpoints, Jobs, and Buckets Power Search on Papers with Code
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Hugging Face Blog11 min read
Measuring benchmark optimization in speech recognition
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Hugging Face Blog10 min read
Up to 3.2x Faster Inference with LFM2.5-DSpark
Today, we release DSpark draft model checkpoints for three models from our LFM2.5 family: LFM2.5-1.2B-Instruct, LFM2.5-2.6B, and LFM2.5-8B-A1B. These add a speculative decoding path that trades a minimal memory increase for a large decoding speedup without changing output quality:
Hugging Face Blog6 min read
How Much Memory Does Your Agent Actually Need?
Equipping an agent with agentic memory sounds simple: distill lessons from its past work, put them back in context, and more experience should mean better performance. It doesn't always work that way.
Hugging Face Blog8 min read
Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Hugging Face Blog41 min read
Same Cluster, 33 Points More Utilization: What Changed Was the Order
The previous post argued that utilization, not intelligence, is where the next real constraint in enterprise AI is forming, and it closed by noting that no playbook has emerged yet for what a mature GPU Management practice looks like. This is ours.
Hugging Face Blog13 min read
State of Open Models: Summer 2026 Observations
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Hugging Face Blog12 min read
Record, train, and deploy from one place with Strands Agents, LeRobot, and Hugging Face Storage Buckets
You have an agent that can already record a demonstration and push it to the Hugging Face Hub. Now you want to run that loop continuously: collect episodes through the day, train a policy on the growing dataset, deploy it, and pull the next batch back to improve it.
Hugging Face Blog20 min read
Showing 54 of 55 stories
Load more storiesAiByts Weekly Brief
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts