Community Blog & Articles

Community Articles

🧨 Stable Diffusion in JAX / Flax !

Optimization story: Bloom inference

Introducing DOI: the Digital Object Identifier to Datasets and Models

Japanese Stable Diffusion

Very Large Language Models and How to Evaluate Them

Image Classification with AutoTrain

How 🤗 Accelerate runs very large models thanks to PyTorch

SetFit: Efficient Few-Shot Learning Without Prompts

Ethics and Society Newsletter #1

Incredibly Fast BLOOM Inference with DeepSpeed and Accelerate

What's new in Diffusers? 🎨

Train your first Decision Transformer

How to train a Language Model with Megatron-LM

OpenRAIL: Towards open and responsible AI licensing frameworks

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

Community Blog & Articles

Impactful scheduling for GPU clusters

UltraBERT: One Encoder for Classification and Retrieval

Tokenmaxxing BERT: 50x faster tokenization

The Missing Piece in LLM Memory: Why Long Context and Retrieval Aren't Enough for Belief Revision

Apertus 1.5 Release Notes

Introducing Lumma-Fev-27B

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

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

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

When agents self-improve, what should persist?

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

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

One Decision Model Instead of a Ranking Team: Short-Video and News Recommendation with autotrust/JEV-27B-VL

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

New in llama.cpp: Decision Models

One Model Family, Two Gold-Level Results: Fine-Tuning Nemotron for IOI and IMO

Multimodal open d1 decision models for the edge

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

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

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

🧨 Stable Diffusion in JAX / Flax !

Optimization story: Bloom inference

Introducing DOI: the Digital Object Identifier to Datasets and Models

Japanese Stable Diffusion

Very Large Language Models and How to Evaluate Them

Image Classification with AutoTrain

How 🤗 Accelerate runs very large models thanks to PyTorch

SetFit: Efficient Few-Shot Learning Without Prompts

Ethics and Society Newsletter #1

Incredibly Fast BLOOM Inference with DeepSpeed and Accelerate

What's new in Diffusers? 🎨

Train your first Decision Transformer

How to train a Language Model with Megatron-LM

OpenRAIL: Towards open and responsible AI licensing frameworks

Impactful scheduling for GPU clusters

UltraBERT: One Encoder for Classification and Retrieval

Tokenmaxxing BERT: 50x faster tokenization

The Missing Piece in LLM Memory: Why Long Context and Retrieval Aren't Enough for Belief Revision

Apertus 1.5 Release Notes

Introducing Lumma-Fev-27B

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

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

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

When agents self-improve, what should persist?

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

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

One Decision Model Instead of a Ranking Team: Short-Video and News Recommendation with autotrust/JEV-27B-VL

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

New in llama.cpp: Decision Models

One Model Family, Two Gold-Level Results: Fine-Tuning Nemotron for IOI and IMO

Multimodal open d1 decision models for the edge

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

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

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