社区博客与文章

You can also read this blog in English

Community Articles

Two Years of Local AI on a Laptop: When Open Models Outpaced Moore's Law

Training-Free Reasoning at 88.89% on GPQA Diamond: How Darwin Family Hit Frontier Scores Without a Single Gradient Step

Vividh-ASR: Diagnosing and Fixing Studio-Bias in Whisper for Indic Languages

KV Caching Explained: Optimizing Transformer Inference Efficiency

NEO-unify: Building Native Multimodal Unified Models End to End

CyberSecQwen-4B: Why Defensive Cyber Needs Small, Specialized, Locally-Runnable Models

lablab-ai-amd-developer-hackathon

How to Comply with SOC 2 and ISO 27001 with Hugging Face: A Practical Guide to AI Model Supply Chain Governance

Uncensor any LLM with abliteration

Code a simple RAG from scratch

QVAC MedPsy: State-of-the-Art Medical and Healthcare Language Models for Edge Devices

Pallas for people who know JAX but not kernels yet

Safety Evals Should Project Test-Time Compute

You do the work. Big Tech takes the model.

Self Evolving is the Endgame or final destiny

makeMoE: Implement a Sparse Mixture of Experts Language Model from Scratch

Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment

Small Language Models (SLM): A Comprehensive Overview

Common AI Model Formats

DualPipe Explained: A Comprehensive Guide to DualPipe That Anyone Can Understand—Even Without a Distributed Training Background

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

基于 Transformers 的编码器-解码器模型

2020年10月10日

Reformer 模型 - 突破语言建模的极限

2020年7月3日

如何生成文本：通过 Transformers 用不同的解码方法生成文本

2020年3月1日

Community Articles

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

Two Years of Local AI on a Laptop: When Open Models Outpaced Moore's Law

Training-Free Reasoning at 88.89% on GPQA Diamond: How Darwin Family Hit Frontier Scores Without a Single Gradient Step

Vividh-ASR: Diagnosing and Fixing Studio-Bias in Whisper for Indic Languages

KV Caching Explained: Optimizing Transformer Inference Efficiency

NEO-unify: Building Native Multimodal Unified Models End to End

CyberSecQwen-4B: Why Defensive Cyber Needs Small, Specialized, Locally-Runnable Models

lablab-ai-amd-developer-hackathon

How to Comply with SOC 2 and ISO 27001 with Hugging Face: A Practical Guide to AI Model Supply Chain Governance

Uncensor any LLM with abliteration

Code a simple RAG from scratch

QVAC MedPsy: State-of-the-Art Medical and Healthcare Language Models for Edge Devices

Pallas for people who know JAX but not kernels yet

Safety Evals Should Project Test-Time Compute

You do the work. Big Tech takes the model.

Self Evolving is the Endgame or final destiny

makeMoE: Implement a Sparse Mixture of Experts Language Model from Scratch

Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment

Small Language Models (SLM): A Comprehensive Overview

Common AI Model Formats

DualPipe Explained: A Comprehensive Guide to DualPipe That Anyone Can Understand—Even Without a Distributed Training Background

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

View all articles