Community Blog & Articles

Community Articles

Advantage Actor Critic (A2C)

How to train your model dynamically using adversarial data

The Technology Behind BLOOM Training

Building a Playlist Generator with Sentence Transformers

Introducing The World's Largest Open Multilingual Language Model: BLOOM

Getting Started with Sentiment Analysis on Twitter

Policy Gradient with PyTorch

Liftoff! How to get started with your first ML project 🚀

Accelerate Large Model Training using DeepSpeed

Announcing Evaluation on the Hub

Getting Started With Embeddings

Convert Transformers to ONNX with Hugging Face Optimum

Intel and Hugging Face Partner to Democratize Machine Learning Hardware Acceleration

Director of Machine Learning Insights [Part 3: Finance Edition]

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

Community Blog & Articles

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

autotrust/JEV-27B: fast, calibrated decisions and full reasoning from one open model

New in llama.cpp: Decision Models

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

NVIDIA Kumo Tabular Sets a New Accuracy-Efficiency Frontier for Tabular Prediction

Carbon-A: Finding genes in known and unknown genomes

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

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

Open-sourcing AstaBrief, the fast report-generation model in Asta

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

Universal Modder: A Practical Guide to AI Game Modding

KV Caching Explained: Optimizing Transformer Inference Efficiency

Leading the System One Mosaic Benchmark: What Darwin-27B-ZTC-v2's #1 Means

Uncensor any LLM with abliteration

Decoding LLM Alignment: A Concise Guide for GRPO and its variants

ViDiHand: The Surprising Effectiveness of Video Diffusion Models for Hand Motion Reconstruction

EuroLLM-9B

FiftyOne Now Reads LeRobot: 50 Embodiments, 497 Episodes, One Indexed Dataset

OpenAI Decisions API vs. Jev: A Practical Guide to Decision Models

Live Human Feedback in the Training Loop: Aligning Diffusion Models with Real People

Advantage Actor Critic (A2C)

How to train your model dynamically using adversarial data

The Technology Behind BLOOM Training

Building a Playlist Generator with Sentence Transformers

Introducing The World's Largest Open Multilingual Language Model: BLOOM

Getting Started with Sentiment Analysis on Twitter

Policy Gradient with PyTorch

Liftoff! How to get started with your first ML project 🚀

Accelerate Large Model Training using DeepSpeed

Announcing Evaluation on the Hub

Getting Started With Embeddings

Convert Transformers to ONNX with Hugging Face Optimum

Intel and Hugging Face Partner to Democratize Machine Learning Hardware Acceleration

Director of Machine Learning Insights [Part 3: Finance Edition]

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

autotrust/JEV-27B: fast, calibrated decisions and full reasoning from one open model

New in llama.cpp: Decision Models

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

NVIDIA Kumo Tabular Sets a New Accuracy-Efficiency Frontier for Tabular Prediction

Carbon-A: Finding genes in known and unknown genomes

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

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

Open-sourcing AstaBrief, the fast report-generation model in Asta

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

Universal Modder: A Practical Guide to AI Game Modding

KV Caching Explained: Optimizing Transformer Inference Efficiency

Leading the System One Mosaic Benchmark: What Darwin-27B-ZTC-v2's #1 Means

Uncensor any LLM with abliteration

Decoding LLM Alignment: A Concise Guide for GRPO and its variants

ViDiHand: The Surprising Effectiveness of Video Diffusion Models for Hand Motion Reconstruction

EuroLLM-9B

FiftyOne Now Reads LeRobot: 50 Embodiments, 497 Episodes, One Indexed Dataset

OpenAI Decisions API vs. Jev: A Practical Guide to Decision Models

Live Human Feedback in the Training Loop: Aligning Diffusion Models with Real People