社区博客与文章

Community Articles

After the party comes the free lunch: regularizing ColBERT models to enhance pooling capabilities and reduce index footprint

Meet Cohere Transcribe Arabic

NVIDIA Isaac Teleop and GR00T 1.7 Open VLA Model Available in LeRobot

Atom2.7m: Representation-Level Specialization for Arithmetic-Aware Small Language Models

Where Does the Signal Live? <br> A Web Data Recipe for Medical Encoder Pretraining

Putting DoctoBERT to Work: A Practical Guide

Mastering Tensor Dimensions in Transformers

A Guide to Reinforcement Learning Post-Training for LLMs: PPO, DPO, GRPO, and Beyond

80TB+ of astronomy for the HDD-poor: crossmatch the Multimodal Universe from your laptop

Agentic RL: Token-In, Token-Out Done Right

Arcee Becomes the First Major American AI Lab to Replace AWS S3 with Hugging Face Private Storage, in a Multi-Million Dollar Commercial Partnership

PyTorch 性能剖析（第 2 部分）：从 nn.Linear 到融合 MLP

2026年6月11日

torchprofileCUDA

PyTorch 性能剖析（第 1 部分）：torch.profiler 入门指南

2026年5月29日

llmfine-tuningopen-source

Codex 正在推动 AI 模型的开源与训练流程

2025年12月11日

partnershipsgoogleannouncement

构建开放的未来——我们与 Google Cloud 的全新合作伙伴关系

2025年11月13日

lerobotrobotics

使用 NVIDIA Isaac 构建医疗机器人：从仿真到部署

2025年10月29日

ethicsguidespeech

经同意的语音克隆

2025年10月28日

datasetsxethub

流式数据集：效率提升 100 倍

2025年10月27日

huggingface_hubpythonannouncement

huggingface_hub v1.0：开源机器学习基础五周年回顾

2025年10月27日

lerobotrobotics

LeRobot v0.4.0：全面提升开源机器人的学习能力

2025年10月24日

ocrvisionmultimodal

用开源模型强化你的 OCR 工作流

2025年10月21日

datasetsopen-sourcevision

用 AI Sheets 解锁图像的力量

2025年10月21日

transformerspytorchoptimization

来自OpenAI gpt-oss的技巧，你🫵在transformers中也可以使用

2025年9月11日

spaceszerogpupytorch

ZeroGPU Spaces 加速实践：PyTorch Ahead-of-Time Compilation 全解析

2025年9月2日

mcpllmqwen

用 Claude 和 Hugging Face 生成图像

2025年8月19日

Community Articles

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

VKUE: No GPU? Runs Anyway — a 34.7B Reasoner on a Laptop and on Bare CPU

Distillation in 2026 (so far): which frontier models use it and how

After the party comes the free lunch: regularizing ColBERT models to enhance pooling capabilities and reduce index footprint

Meet Cohere Transcribe Arabic

NVIDIA Isaac Teleop and GR00T 1.7 Open VLA Model Available in LeRobot

Atom2.7m: Representation-Level Specialization for Arithmetic-Aware Small Language Models

How to visualize any Hugging Face model

Why Whisper cuts off Indic transcripts after six seconds

Teaching a coding agent to deploy production endpoints on Amazon SageMaker

Can Codex Handle Real-World Data Analysis?

Can Skills Improve Codex’s Data Analysis Capabilities?

Code a simple RAG from scratch

KV Caching Explained: Optimizing Transformer Inference Efficiency

Where Does the Signal Live? <br> A Web Data Recipe for Medical Encoder Pretraining

Putting DoctoBERT to Work: A Practical Guide

Mastering Tensor Dimensions in Transformers

A Guide to Reinforcement Learning Post-Training for LLMs: PPO, DPO, GRPO, and Beyond

80TB+ of astronomy for the HDD-poor: crossmatch the Multimodal Universe from your laptop

Agentic RL: Token-In, Token-Out Done Right

Arcee Becomes the First Major American AI Lab to Replace AWS S3 with Hugging Face Private Storage, in a Multi-Million Dollar Commercial Partnership

社区博客与文章

VKUE: No GPU? Runs Anyway — a 34.7B Reasoner on a Laptop and on Bare CPU

Distillation in 2026 (so far): which frontier models use it and how

After the party comes the free lunch: regularizing ColBERT models to enhance pooling capabilities and reduce index footprint

Meet Cohere Transcribe Arabic

NVIDIA Isaac Teleop and GR00T 1.7 Open VLA Model Available in LeRobot

Atom2.7m: Representation-Level Specialization for Arithmetic-Aware Small Language Models

How to visualize *any* Hugging Face model

Why Whisper cuts off Indic transcripts after six seconds

Teaching a coding agent to deploy production endpoints on Amazon SageMaker

Can Codex Handle Real-World Data Analysis?

Can Skills Improve Codex’s Data Analysis Capabilities?

Code a simple RAG from scratch

KV Caching Explained: Optimizing Transformer Inference Efficiency

Where Does the Signal Live? <br> A Web Data Recipe for Medical Encoder Pretraining

Putting DoctoBERT to Work: A Practical Guide

Mastering Tensor Dimensions in Transformers

A Guide to Reinforcement Learning Post-Training for LLMs: PPO, DPO, GRPO, and Beyond

80TB+ of astronomy for the HDD-poor: crossmatch the Multimodal Universe from your laptop

Agentic RL: Token-In, Token-Out Done Right

Arcee Becomes the First Major American AI Lab to Replace AWS S3 with Hugging Face Private Storage, in a Multi-Million Dollar Commercial Partnership

PyTorch 性能剖析（第 2 部分）：从 nn.Linear 到融合 MLP

PyTorch 性能剖析（第 1 部分）：torch.profiler 入门指南

Codex 正在推动 AI 模型的开源与训练流程

构建开放的未来——我们与 Google Cloud 的全新合作伙伴关系

使用 NVIDIA Isaac 构建医疗机器人：从仿真到部署

经同意的语音克隆

流式数据集：效率提升 100 倍

huggingface_hub v1.0：开源机器学习基础五周年回顾

LeRobot v0.4.0：全面提升开源机器人的学习能力

用开源模型强化你的 OCR 工作流

用 AI Sheets 解锁图像的力量

来自OpenAI gpt-oss的技巧，你🫵在transformers中也可以使用

ZeroGPU Spaces 加速实践：PyTorch Ahead-of-Time Compilation 全解析

用 Claude 和 Hugging Face 生成图像

VKUE: No GPU? Runs Anyway — a 34.7B Reasoner on a Laptop and on Bare CPU

Distillation in 2026 (so far): which frontier models use it and how

After the party comes the free lunch: regularizing ColBERT models to enhance pooling capabilities and reduce index footprint

Meet Cohere Transcribe Arabic

NVIDIA Isaac Teleop and GR00T 1.7 Open VLA Model Available in LeRobot

Atom2.7m: Representation-Level Specialization for Arithmetic-Aware Small Language Models

How to visualize *any* Hugging Face model

Why Whisper cuts off Indic transcripts after six seconds

Teaching a coding agent to deploy production endpoints on Amazon SageMaker

Can Codex Handle Real-World Data Analysis?

Can Skills Improve Codex’s Data Analysis Capabilities?

Code a simple RAG from scratch

KV Caching Explained: Optimizing Transformer Inference Efficiency

Where Does the Signal Live? <br> A Web Data Recipe for Medical Encoder Pretraining

Putting DoctoBERT to Work: A Practical Guide

Mastering Tensor Dimensions in Transformers

A Guide to Reinforcement Learning Post-Training for LLMs: PPO, DPO, GRPO, and Beyond

80TB+ of astronomy for the HDD-poor: crossmatch the Multimodal Universe from your laptop

Agentic RL: Token-In, Token-Out Done Right

Arcee Becomes the First Major American AI Lab to Replace AWS S3 with Hugging Face Private Storage, in a Multi-Million Dollar Commercial Partnership

How to visualize any Hugging Face model

How to visualize any Hugging Face model