社区博客与文章

Community Articles

view all

Quantum Cryptanalysis on Real Hardware: Pushing Symmetric-Structure Key Recovery Beyond the Published Frontier

FINAL-Bench

•

6 days ago

• 15

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

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

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

Why Whisper cuts off Indic transcripts after six seconds

Can Codex Handle Real-World Data Analysis?

Can Skills Improve Codex’s Data Analysis Capabilities?

Fine-Tuning Your First Large Language Model (LLM) with PyTorch and Hugging Face

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

Adding a GPU Without Building One

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

2024年9月18日

datasetssqlduckdb

为数据集而生的 SQL 控制台

2024年9月17日

guide

Accelerate 1.0.0

2024年9月13日

paddingpackingFlash Attention 2

通过打包 Flash Attention 来提升 Hugging Face 训练效率

2024年8月21日

long-contextinfini-attentionmemory-compression

一次失败的实验——无限注意力，我们为什么坚持实验

2024年8月14日

guidecommunityggml

ggml 简介

2024年8月13日

nlpcommunityresearch

Falcon Mamba: 首个高效的无注意力机制 7B 模型

2024年8月12日

LLMnlpcommunity

对 LLM 工具使用进行统一

2024年8月12日

announcemententerprisehub

XetHub 加入 Hugging Face!

2024年8月8日

nlpcommunityresearch

Google 最新发布： Gemma 2 2B, ShieldGemma 和 Gemma Scope

2024年7月31日

diffusersguidediffusion-transformers

基于 Quanto 和 Diffusers 的内存高效 transformer 扩散模型

2024年7月30日

communityevaluationsynthetic-data

LAVE：使用 LLM 对 Docmatix 进行零样本 VQA 评估 - 我们还需要微调吗？

2024年7月25日

nlpcommunityresearch

Llama 3.1：405B/70B/8B 模型的多语言与长上下文能力解析

2024年7月23日

communitydatasetssynthetic-data

Docmatix - 超大文档视觉问答数据集

2024年7月18日

Community Articles

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

Quantum Cryptanalysis on Real Hardware: Pushing Symmetric-Structure Key Recovery Beyond the Published Frontier

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

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

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

Code a simple RAG from scratch

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

Meet Cohere Transcribe Arabic

Mastering Tensor Dimensions in Transformers

How to visualize any Hugging Face model

Teaching a coding agent to deploy production endpoints on Amazon SageMaker

KV Caching Explained: Optimizing Transformer Inference Efficiency

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

Why Whisper cuts off Indic transcripts after six seconds

Can Codex Handle Real-World Data Analysis?

Can Skills Improve Codex’s Data Analysis Capabilities?

Fine-Tuning Your First Large Language Model (LLM) with PyTorch and Hugging Face

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

Adding a GPU Without Building One

社区博客与文章

Quantum Cryptanalysis on Real Hardware: Pushing Symmetric-Structure Key Recovery Beyond the Published Frontier

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

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

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

Code a simple RAG from scratch

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

Meet Cohere Transcribe Arabic

Mastering Tensor Dimensions in Transformers

How to visualize *any* Hugging Face model

Teaching a coding agent to deploy production endpoints on Amazon SageMaker

KV Caching Explained: Optimizing Transformer Inference Efficiency

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

Why Whisper cuts off Indic transcripts after six seconds

Can Codex Handle Real-World Data Analysis?

Can Skills Improve Codex’s Data Analysis Capabilities?

Fine-Tuning Your First Large Language Model (LLM) with PyTorch and Hugging Face

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

Adding a GPU Without Building One

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

为数据集而生的 SQL 控制台

Accelerate 1.0.0

通过打包 Flash Attention 来提升 Hugging Face 训练效率

一次失败的实验——无限注意力，我们为什么坚持实验

ggml 简介

Falcon Mamba: 首个高效的无注意力机制 7B 模型

对 LLM 工具使用进行统一

XetHub 加入 Hugging Face!

Google 最新发布： Gemma 2 2B, ShieldGemma 和 Gemma Scope

基于 Quanto 和 Diffusers 的内存高效 transformer 扩散模型

LAVE：使用 LLM 对 Docmatix 进行零样本 VQA 评估 - 我们还需要微调吗？

Llama 3.1：405B/70B/8B 模型的多语言与长上下文能力解析

Docmatix - 超大文档视觉问答数据集

Quantum Cryptanalysis on Real Hardware: Pushing Symmetric-Structure Key Recovery Beyond the Published Frontier

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

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

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

Code a simple RAG from scratch

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

Meet Cohere Transcribe Arabic

Mastering Tensor Dimensions in Transformers

How to visualize *any* Hugging Face model

Teaching a coding agent to deploy production endpoints on Amazon SageMaker

KV Caching Explained: Optimizing Transformer Inference Efficiency

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

Why Whisper cuts off Indic transcripts after six seconds

Can Codex Handle Real-World Data Analysis?

Can Skills Improve Codex’s Data Analysis Capabilities?

Fine-Tuning Your First Large Language Model (LLM) with PyTorch and Hugging Face

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

Adding a GPU Without Building One

How to visualize any Hugging Face model

How to visualize any Hugging Face model