Hugging Face
O repositório onde os modelos abertos moram, e o blog que anuncia cada um.
Hugging Face Hub · Transformers
1 fonte oficial monitorada · última atualização em 08/10/2026
Novidades recentes
40 atualizações
- Outros·oficial·
The model that didn't exist, so you made it yourself
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
- Outros·oficial·
Multimodal open d1 decision models for the edge
A Blog post by Liquid AI on Hugging Face
- Outros·oficial·
Introducing Falcon ASR
A Blog post by Technology Innovation Institute on Hugging Face
- Outros·oficial·
One Model Family, Two Gold-Level Results: Fine-Tuning Nemotron for IOI and IMO
A Blog post by NVIDIA on Hugging Face
- Outros·oficial·
Falcon-Emirati: When an LLM Learns the Dialect, the Culture, and the Nuance
A Blog post by Technology Innovation Institute on Hugging Face
- Outros·oficial·
The Agent Said It Was Done. The Database Disagreed.
A Blog post by Microsoft on Hugging Face
- Outros·oficial·
Open-sourcing AstaBrief, the fast report-generation model in Asta
A Blog post by Ai2 on Hugging Face
- Outros·oficial·
AutoSynthData: Generating Training Data for Enterprise Agents
A Blog post by ServiceNow-AI on Hugging Face
- Outros·oficial·
Introducing Olmo-core 3: Open, scalable training infrastructure for large MoEs
A Blog post by Ai2 on Hugging Face
- Pesquisa·oficial·
Open TTS Leaderboard: Scalable Evaluation for Multilingual Text-to-Speech and Voice Cloning
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
- Outros·oficial·
NVIDIA Kumo Tabular Sets a New Accuracy-Efficiency Frontier for Tabular Prediction
A Blog post by NVIDIA on Hugging Face
- Outros·oficial·
Getting the Source Right, Not Just the Fact: Source-Aware Verification for MCP Agents
A Blog post by Multiverse Computing on Hugging Face
- Outros·oficial·
Holo4: powering generalist computer-use agents
A Blog post by H company on Hugging Face
- Outros·oficial·
Welcome RL Environments to the hub
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
- Outros·oficial·
Accelerating vision-language models with LFM2.5-VL-DSpark
A Blog post by Liquid AI on Hugging Face
- Outros·oficial·
How to Use NVIDIA Warp and MjWarp to Accelerate Robotics Simulation and Learning Workflows
A Blog post by NVIDIA on Hugging Face
- Outros·oficial·
How UK AISI and EvalEval Are Making Benchmark Results Reproducible
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
- Outros·oficial·
Transformers now runs llama.cpp quants
- Empresa·oficial·
Jun Kim, oMLX creator and maintainer, joins Hugging Face to support the MLX community
- Outros·oficial·
Pruning LLMs Like a Physicist: Block Removal as an Ising Optimization Problem
A Blog post by Multiverse Computing on Hugging Face
- Outros·oficial·
tokenizers v1: encode, decode and scaling, measured
- Outros·oficial·
Your Agent Aced the Task. Will It Do It Again?
- Outros·oficial·
Rebuilding AUTOMATIC1111 with Gradio Workflow
- Outros·oficial·
Async GRPO with LoRA across HF Jobs: a bucket, a proxy, and no NCCL
- Pesquisa·oficial·
IBM releases SOTA Granite Time Series PatchTST-FM-r2 model with commercial-friendly license
A Blog post by IBM Research on Hugging Face
- Outros·oficial·
Safety for Whom? Refusing the Right Subset of a Topic, Not the Whole Topic
A Blog post by Multiverse Computing on Hugging Face
- Outros·oficial·
NeoMME: an efficient Multimodal-native and Multilingual Encoder
data informada pela fonte; encontrada pelo radar em 09 de out. de 2026
- Outros·oficial·
Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps
data informada pela fonte; encontrada pelo radar em 09 de out. de 2026
- Outros·oficial·
Give Your Coding Agents a Memory You Own
data informada pela fonte; encontrada pelo radar em 09 de out. de 2026
- Outros·oficial·
Training a coding model to paint watercolours with TRL and OpenEnv
data informada pela fonte; encontrada pelo radar em 09 de out. de 2026
- Pesquisa·oficial·
Real-Time Intelligence with IBM Time Series Models on Confluent
A Blog post by IBM Research on Hugging Face
- Outros·oficial·
BenchMIRT: What are LLM benchmarks actually measuring?
data informada pela fonte; encontrada pelo radar em 09 de out. de 2026
- Outros·oficial·
Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI
data informada pela fonte; encontrada pelo radar em 09 de out. de 2026
- Outros·oficial·
The Open ASR Leaderboard Adds Its First Global South Language
data informada pela fonte; encontrada pelo radar em 09 de out. de 2026
- Outros·oficial·
Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers
data informada pela fonte; encontrada pelo radar em 09 de out. de 2026
- Outros·oficial·
LLMs Granite 4.2: como foram construídos
Publicação da IBM Granite no Hugging Face.
traduzido por IA · claude-opus-5
original: “Granite 4.2 LLMs: How They're Built”
data informada pela fonte; encontrada pelo radar em 09 de out. de 2026
- Outros·oficial·
Quantization-Aware Healing: modelo comprimido em 4 bits que supera o original em precisão total
original: “Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original”
data informada pela fonte; encontrada pelo radar em 09 de out. de 2026
- Outros·oficial·
Conecte, execute e publique: fluxos de trabalho de IA no Gradio
original: “Wire It, Run It, Deploy It: AI Workflows in Gradio”
data informada pela fonte; encontrada pelo radar em 09 de out. de 2026
- Outros·oficial·
Como Inference Endpoints, Jobs e Buckets movem a busca no Papers
Publicação do Hugging Face sobre a infraestrutura por trás da busca na seção de artigos.
traduzido por IA · claude-opus-5
original: “How Hugging Face Inference Endpoints, Jobs, and Buckets Power Search on Papers with Code”
data informada pela fonte; encontrada pelo radar em 09 de out. de 2026
- Outros·oficial·
Medindo a otimização para benchmarks em reconhecimento de fala
Publicação do Hugging Face sobre o quanto os modelos de reconhecimento de fala estão sendo ajustados especificamente para os benchmarks.
traduzido por IA · claude-opus-5
original: “Measuring benchmark optimization in speech recognition”
data informada pela fonte; encontrada pelo radar em 09 de out. de 2026
Fontes monitoradas
O radar lê estes endereços automaticamente. A ordem é a de prioridade: se a primeira falhar, as seguintes continuam entregando.
- 1. https://huggingface.co/blog/feed.xml (rss)