Parameter Quantization

Complete DeepSeek-R1 671B Local Deployment Tutorial

by
Complete DeepSeek-R1 671B Local Deployment Tutorial

Click on the above “Beginner Learning Visuals“, select “Star” or “Pin“ Heavyweight content delivered first-hand The following article comes from the WeChat public account: Datawhale Author: Li Xihan Link: https://mp.weixin.qq.com/s/dKfQfv78ch4IlzBML9Tmkw This article is for academic sharing only. If there is any infringement, please contact the backend for deletion Introduction During the recent Spring Festival, DeepSeek … Read more

Summary of Convolutional Neural Network Compression Methods

by
Summary of Convolutional Neural Network Compression Methods

Click on the above “Beginner Learning Vision”, choose to add Star Mark or Top. Important content delivered at the first time For academic sharing only, does not represent the position of this public account, contact for deletion if infringing Reprinted from: Author | Tang Fen@Zhihu Source | https://zhuanlan.zhihu.com/p/359627280 Editor | Jishi Platform We know that … Read more

Practical Experience in Transformer Quantization Deployment Based on Journey 5 Chip

by
Practical Experience in Transformer Quantization Deployment Based on Journey 5 Chip

Introduction: On March 28, the 16th lecture of the “New Youth in Autonomous Driving” organized by Zhixingshi successfully concluded. In this lecture, Yang Zhigang, the core developer of the Horizon toolchain, conducted a live explanation on the topic of “Practical Experience in Transformer Quantization Deployment Based on Journey 5 Chip.” Yang Zhigang first introduced the … Read more

Conversion and Quantization of Multimodal Large Models for Robots

by
Conversion and Quantization of Multimodal Large Models for Robots

1. Introduction In today’s field of artificial intelligence, the application of multimodal large models in robotics is becoming increasingly widespread. This article aims to introduce how to convert multimodal large models to the gguf format and quantize them for efficient deployment on the ollama platform. Through this process, we achieve more efficient model operation and … Read more

Overview of Compact 1-Bit Convolutional Neural Networks via Bayesian Learning

by
Overview of Compact 1-Bit Convolutional Neural Networks via Bayesian Learning

The “Quick Overview” series of articles aims to disseminate important results from conferences and journals in the field of image graphics, allowing readers to quickly understand relevant academic dynamics in their native language through short articles. We welcome attention and submissions~ ◆ ◆ ◆ ◆ Compact 1-Bit Convolutional Neural Networks (BONN) Based on Bayesian Learning … Read more

6 Methods for Compressing Convolutional Neural Networks

by
6 Methods for Compressing Convolutional Neural Networks

This articleis approximately 5200 words, recommended reading time is10+minutes We know that, to some extent, the deeper the network, the more parameters it has, and the more complex the model, the better its final performance. The compression algorithm for neural networks aims to transform a large and complex pre-trained model into a streamlined smaller model. … Read more