Large model generation is accelerated by 2 times! A single GPU can be fine-tuned in a few hours, Peking University School of Mathematics alumni jointly work on open source - Code World

Large model generation is accelerated by 2 times! A single GPU can be fine-tuned in a few hours, Peking University School of Mathematics alumni jointly work on open source

News 2023-09-19 10:10:18 views: null

NoSuchKey

Guess you like

Origin blog.csdn.net/QbitAI/article/details/132959349

Large model generation is accelerated by 2 times! A single GPU can be fine-tuned in a few hours, Peking University School of Mathematics alumni jointly work on open source

FreeWilly2 open source language model fine-tuned based on LLaMA-2

Peking University officially released ChatLaw, a large Chinese legal model, and made it open source

CodeShell, a large open source code model of Peking University, provides supporting IDE plug-ins

The large model can be fine-tuned with very little data, and this article explains the operation principle of LoRA and other methods in detail

ICML 2023 Outstanding Papers Reduced to 6 Substantially! Alumni of Peking University and Wuhan Institute of Technology won awards, and large model watermarks were favored

LLaMA 2: Open Foundation and Fine-Tuned Chat Models

ChatGenTitle: A paper title generation model fine-tuned on the LLaMA model using information from millions of arXiv papers

The seventh of the large language model - Llama-2 single GPU fine-tuning SFT

Only high school mathematics can find algorithms? How powerful is Google's open source AutoML-Zero

Suzhou University launched the open source large model OpenBA; Alibaba Cloud opened the open source Tongyi Qianwen 14B model; Baichuan Intelligent released the Baichuan2-53B closed source large model丨Daily events...

Microsoft has won again! Jointly released Llama 2, an open source AI model for free commercial applications

Became a tenured professor at MIT at the age of 35! Peking University Mathematics "Golden Generation" Won Another Award

Open Source Large Model Ranking

Easily play open source large language model bloom (2)

The most powerful open source large model? Interpretation of Llama 2 Paper

Meta dropped another bomb on the open source community! Publish AI code generation SOTA large model Code Llama

Peking University School of Software and Microelectronics

Tsinghua University teamed up with ByteDance to open source auditory large language model SALMONN

DISC-LawLLM: The Fudan University team released a Chinese smart legal system, built a judicial evaluation benchmark, and open sourced 300,000 fine-tuned data...

Pose Anything is officially open source | A single model can realize key point positioning of any target category

"Learning Python by Reading Comics" 1 and 2 edition sharing, the best introductory tutorial on python, middle school students can learn it in their spare time, and Peking University professors define it this way after reading it

LLMs scaling instruction model Scaling instruction models FLAN (Fine-tuned LAnguage Net, fine-tuned language network)

Fudan team open source large model MOSS

【Large model】—LangChain open source framework introduction

Open source large model application development

School Source Tour丨Open Atom Open Source Foundation visited Nanjing University and Nanjing University of Technology

Open Source Daily | Peking University interns attacked ByteDance’s AI training cluster; Bitwarden further deviated from open source; new generation MoE architecture; installing Linux on mobile phones; what is Nvidia’s real moat?

Get GPT-3 hyperparameters with a single GPU! Train a small model first, then "one-click migration" | Open source

Get GPT-3 hyperparameters with a single GPU! Train a small model first, then "one-click migration" | Open source

Recommended

Ranking

go common records

SVN power failure recovery

深入理解Redis集群主从复制原理

【二叉树】左叶子之和

[1] The first basic syntax Detailed Kotlin

Linux Ansible creates tasks and executes them

vmware ubuntu virtual machine boots online courses

Use Nodejs to crawl certain data from the web page and write the crawled data into excel (see the next article for the front-end part and the server-side part)

Principle underlying thread pool

The number of bytes occupied when char[ ] is initialized

Daily

More

2025-03-22(0)

2025-03-21(0)

2025-03-20(0)

2025-03-19(0)

2025-03-18(0)

2025-03-17(0)

2025-03-16(0)

2025-03-15(0)

2025-03-14(0)

2025-03-13(0)