Blog, Articles, and discussions

From Zero to GPU: A Guide to Building and Scaling Production-Ready CUDA Kernels

By August 18, 2025 • 2

Community Articles

view all

NVIDIA Releases 3 Million Sample Dataset for OCR, Visual Question Answering, and Captioning Tasks

and 4 others •

7 days ago

• 53

<p style="text-align:center;"> Bridging the Gap: Making Robotics Feel Like Machine Learning </p>

•

6 days ago

• 12

Announcing the Synthetic Online Conversations Dataset (SOC)

•

6 days ago

• 10

Code a simple RAG from scratch

•

Oct 29, 2024

• 156

What’s MXFP4? The 4-Bit Secret Powering OpenAI’s GPT‑OSS Models on Modest Hardware

•

10 days ago

• 10

DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge

•

Feb 7

• 208

Kimina-Prover-RL

and 18 others •

4 days ago

• 7

Uncensor any LLM with abliteration

•

Jun 13, 2024

• 653

KV Caching Explained: Optimizing Transformer Inference Efficiency

•

Jan 30

• 115

Post-Training Isaac GR00T N1.5 for LeRobot SO-101 Arm

and 4 others •

Jun 11

• 80

AWorld Multi-Agent System Hits #1 on GAIA Leaderboard

•

11 days ago

• 25

From GRPO to DAPO and GSPO: What, Why, and How

•

10 days ago

• 10

OpenAI just dropped two massive open-weight models — but how do we separate the reality from the hype?

and 2 others •

9 days ago

• 11

How to Run a Hugging Face Model in JAX (Part 1)

•

30 days ago

• 21

Introducing : 🤏🏻🏭SmolFactory

•

8 days ago

• 5

Building Enterprise-Ready Text Classifiers in Minutes with Adaptive Learning

•

10 days ago

• 12

The Missing Semester of AI for Organizations #1: LLM Security

•

12 days ago

• 8

StarCoder: A State-of-the-Art LLM for Code

By May 4, 2023 • 62

How to Install and Use the Hugging Face Unity API

By May 1, 2023 • 12

Running IF with 🧨 diffusers on a Free Tier Google Colab

By April 26, 2023 • 3

Training a language model with 🤗 Transformers using TensorFlow and TPUs

By April 27, 2023

Databricks ❤️ Hugging Face: up to 40% faster training and tuning of Large Language Models

By April 26, 2023 guest

Introducing HuggingFace blog for Chinese speakers: Fostering Collaboration with the Chinese AI community

By April 24, 2023 • 14

How to host a Unity game in a Space

By April 21, 2023 • 5

Accelerating Hugging Face Transformers with AWS Inferentia2

By April 17, 2023 • 1

Graph Classification with Transformers

By April 14, 2023 • 5

Creating Privacy Preserving AI with Substra

By April 12, 2023 • 2

Snorkel AI x Hugging Face: unlock foundation models for enterprises

By April 6, 2023

StackLLaMA: A hands-on guide to train LLaMA with RLHF

By April 5, 2023 • 43

Ethics and Society Newsletter #3: Ethical Openness at Hugging Face

By March 30, 2023

Fast Inference on Large Language Models: BLOOMZ on Habana Gaudi2 Accelerator

By March 28, 2023 • 2

Community Articles

NVIDIA Releases 3 Million Sample Dataset for OCR, Visual Question Answering, and Captioning Tasks

and 4 others •

7 days ago

• 53

RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation

and 9 others •

7 days ago

• 23

ChatML vs Harmony: Understanding the new Format from OpenAI 🔍

•

9 days ago

• 22

How To Build a News Agent with GPT-OSS, Hugging Face Inference & Gradio

•

4 days ago

• 16

<p style="text-align:center;"> Bridging the Gap: Making Robotics Feel Like Machine Learning </p>

•

6 days ago

• 12

Announcing the Synthetic Online Conversations Dataset (SOC)

•

6 days ago

• 10

Code a simple RAG from scratch

•

Oct 29, 2024

• 156

What’s MXFP4? The 4-Bit Secret Powering OpenAI’s GPT‑OSS Models on Modest Hardware

•

10 days ago

• 10

DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge

•

Feb 7

• 208

Kimina-Prover-RL

and 18 others •

4 days ago

• 7

Uncensor any LLM with abliteration

•

Jun 13, 2024

• 653

KV Caching Explained: Optimizing Transformer Inference Efficiency

•

Jan 30

• 115

Post-Training Isaac GR00T N1.5 for LeRobot SO-101 Arm

and 4 others •

Jun 11

• 80

AWorld Multi-Agent System Hits #1 on GAIA Leaderboard

•

11 days ago

• 25

From GRPO to DAPO and GSPO: What, Why, and How

•

10 days ago

• 10

OpenAI just dropped two massive open-weight models — but how do we separate the reality from the hype?

and 2 others •

9 days ago

• 11

How to Run a Hugging Face Model in JAX (Part 1)

•

30 days ago

• 21

Introducing : 🤏🏻🏭SmolFactory

•

8 days ago

• 5

Building Enterprise-Ready Text Classifiers in Minutes with Adaptive Learning

•

10 days ago

• 12

The Missing Semester of AI for Organizations #1: LLM Security

•

12 days ago

• 8

View all

Blog, Articles, and discussions

From Zero to GPU: A Guide to Building and Scaling Production-Ready CUDA Kernels

NVIDIA Releases 3 Million Sample Dataset for OCR, Visual Question Answering, and Captioning Tasks

RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation

ChatML vs Harmony: Understanding the new Format from OpenAI 🔍

How To Build a News Agent with GPT-OSS, Hugging Face Inference & Gradio

<p style="text-align:center;"> Bridging the Gap: Making Robotics Feel Like Machine Learning </p>

Announcing the Synthetic Online Conversations Dataset (SOC)

Code a simple RAG from scratch

What’s MXFP4? The 4-Bit Secret Powering OpenAI’s GPT‑OSS Models on Modest Hardware

DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge

Kimina-Prover-RL

Uncensor any LLM with abliteration

KV Caching Explained: Optimizing Transformer Inference Efficiency

Post-Training Isaac GR00T N1.5 for LeRobot SO-101 Arm

AWorld Multi-Agent System Hits #1 on GAIA Leaderboard

From GRPO to DAPO and GSPO: What, Why, and How

OpenAI just dropped two massive open-weight models — *but how do we separate the reality from the hype?*

How to Run a Hugging Face Model in JAX (Part 1)

Introducing : 🤏🏻🏭SmolFactory

Building Enterprise-Ready Text Classifiers in Minutes with Adaptive Learning

The Missing Semester of AI for Organizations #1: LLM Security

StarCoder: A State-of-the-Art LLM for Code

How to Install and Use the Hugging Face Unity API

Running IF with 🧨 diffusers on a Free Tier Google Colab

Training a language model with 🤗 Transformers using TensorFlow and TPUs

Databricks ❤️ Hugging Face: up to 40% faster training and tuning of Large Language Models

Introducing HuggingFace blog for Chinese speakers: Fostering Collaboration with the Chinese AI community

How to host a Unity game in a Space

Accelerating Hugging Face Transformers with AWS Inferentia2

Graph Classification with Transformers

Creating Privacy Preserving AI with Substra

Snorkel AI x Hugging Face: unlock foundation models for enterprises

StackLLaMA: A hands-on guide to train LLaMA with RLHF

Ethics and Society Newsletter #3: Ethical Openness at Hugging Face

Fast Inference on Large Language Models: BLOOMZ on Habana Gaudi2 Accelerator

NVIDIA Releases 3 Million Sample Dataset for OCR, Visual Question Answering, and Captioning Tasks

RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation

ChatML vs Harmony: Understanding the new Format from OpenAI 🔍

How To Build a News Agent with GPT-OSS, Hugging Face Inference & Gradio

<p style="text-align:center;"> Bridging the Gap: Making Robotics Feel Like Machine Learning </p>

Announcing the Synthetic Online Conversations Dataset (SOC)

Code a simple RAG from scratch

What’s MXFP4? The 4-Bit Secret Powering OpenAI’s GPT‑OSS Models on Modest Hardware

DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge

Kimina-Prover-RL

Uncensor any LLM with abliteration

KV Caching Explained: Optimizing Transformer Inference Efficiency

Post-Training Isaac GR00T N1.5 for LeRobot SO-101 Arm

AWorld Multi-Agent System Hits #1 on GAIA Leaderboard

From GRPO to DAPO and GSPO: What, Why, and How

OpenAI just dropped two massive open-weight models — *but how do we separate the reality from the hype?*

How to Run a Hugging Face Model in JAX (Part 1)

Introducing : 🤏🏻🏭SmolFactory

Building Enterprise-Ready Text Classifiers in Minutes with Adaptive Learning

The Missing Semester of AI for Organizations #1: LLM Security

OpenAI just dropped two massive open-weight models — but how do we separate the reality from the hype?

OpenAI just dropped two massive open-weight models — but how do we separate the reality from the hype?