Community Blog & Articles

Community Articles

Llama can now see and run on your device - welcome Llama 3.2

FineVideo: behind the scenes

Exploring the Daily Papers Page on Hugging Face

Optimize and deploy with Optimum-Intel and OpenVINO GenAI

Fine-tuning LLMs to 1.58bit: extreme quantization made easy

Introducing the SQL Console on Datasets

Introducing Community Tools on HuggingChat

Accelerate 1.0.0

Hugging Face partners with TruffleHog to Scan for Secrets

Scaling robotics datasets with video encoding

The 5 Most Under-Rated Tools on Hugging Face

Improving Hugging Face Training Efficiency Through Packing with Flash Attention 2

Deploy Meta Llama 3.1 405B on Google Cloud Vertex AI

A failed experiment: Infini-Attention, and why we should keep trying?

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

Community Blog & Articles

Impactful scheduling for GPU clusters

Multimodal open d1 decision models for the edge

LightOnOCR-3: High-Performance OCR and Layout Extraction in One Model

UltraBERT: One Encoder for Classification and Retrieval

Introducing Lumma-Fev-27B

Carbon-A: Finding genes in known and unknown genomes

Falcon OCR Arabic: 270M Parameters State-of-the-Art Arabic OCR

ColGrep-Agent: Cutting Frontier Coding Agents’ Tokens by a Third

autotrust/JEV-27B-VL: a decision model that learned to see without a single image of training

New in llama.cpp: Decision Models

Darwin-27B-ZTC: A Single-Pass Judge and a Quantitative Look at Its Calibration

UIBK-Embedding-v1: A Dense and a Late-Interaction Retriever in One Model, One Index and One Search

Backpropagation on an Inference-Only NPU: Pretraining VKORE-46M-NPU From Scratch

Falcon-Emirati: When an LLM Learns the Dialect, the Culture, and the Nuance

The Open Quantum Challenge: Quantum Simulation and QEC Decoding on Classical GPUs

Fine-Tune ASR for Your Domain with NVIDIA Speech Agent Skills

Sparseup-fr: A French replication of Linkup's sparse embedding model

Six Questions to Ask a LeRobot Dataset Before You Train

Basis Global Emotions: 525 hours of expressive speech across 108 locales

Introducing Llama Windows: llama.cpp in your Windows tray

Llama can now see and run on your device - welcome Llama 3.2

FineVideo: behind the scenes

Exploring the Daily Papers Page on Hugging Face

Optimize and deploy with Optimum-Intel and OpenVINO GenAI

Fine-tuning LLMs to 1.58bit: extreme quantization made easy

Introducing the SQL Console on Datasets

Introducing Community Tools on HuggingChat

Accelerate 1.0.0

Hugging Face partners with TruffleHog to Scan for Secrets

Scaling robotics datasets with video encoding

The 5 Most Under-Rated Tools on Hugging Face

Improving Hugging Face Training Efficiency Through Packing with Flash Attention 2

Deploy Meta Llama 3.1 405B on Google Cloud Vertex AI

A failed experiment: Infini-Attention, and why we should keep trying?

Impactful scheduling for GPU clusters

Multimodal open d1 decision models for the edge

LightOnOCR-3: High-Performance OCR and Layout Extraction in One Model

UltraBERT: One Encoder for Classification and Retrieval

Introducing Lumma-Fev-27B

Carbon-A: Finding genes in known and unknown genomes

Falcon OCR Arabic: 270M Parameters State-of-the-Art Arabic OCR

ColGrep-Agent: Cutting Frontier Coding Agents’ Tokens by a Third

autotrust/JEV-27B-VL: a decision model that learned to see without a single image of training

New in llama.cpp: Decision Models

Darwin-27B-ZTC: A Single-Pass Judge and a Quantitative Look at Its Calibration

UIBK-Embedding-v1: A Dense and a Late-Interaction Retriever in One Model, One Index and One Search

Backpropagation on an Inference-Only NPU: Pretraining VKORE-46M-NPU From Scratch

Falcon-Emirati: When an LLM Learns the Dialect, the Culture, and the Nuance

The Open Quantum Challenge: Quantum Simulation and QEC Decoding on Classical GPUs

Fine-Tune ASR for Your Domain with NVIDIA Speech Agent Skills

Sparseup-fr: A French replication of Linkup's sparse embedding model

Six Questions to Ask a LeRobot Dataset Before You Train

Basis Global Emotions: 525 hours of expressive speech across 108 locales

Introducing Llama Windows: llama.cpp in your Windows tray