180 billion parameters, supports Chinese, 3.5 trillion training data! Open source ChatGPT-like model - Code World

180 billion parameters, supports Chinese, 3.5 trillion training data! Open source ChatGPT-like model

Enterprise 2023-09-11 20:59:43 views: null

NoSuchKey

Guess you like

Origin blog.csdn.net/huapeng_guo/article/details/132813119

180 billion parameters, supports Chinese, 3.5 trillion training data! Open source ChatGPT-like model

Llama 2's high-profile open source subverts the big model circle! 2 trillion token training, can't beat GPT3.5

ELECTRA Chinese pre-training model of open source, 110 parameters, performance comparable BERT

Run ChatGPT-like open source large language model (LLM) Dolly 2.0 on Intel Sharp™ discrete graphics

The ChatGPT-like model that raised $100 million is open source! Available for commercial use, 8 models

Tencent Tang Daosheng: With over 100 billion parameters and over 2 trillion tokens, Tencent’s Hunyuan large model is fully open to the industry

Microsoft open source DeepSpeed-Chat: make ChatGPT-like 100 billion large models speed up and save money by 15 times

13 billion parameters, 52-layer network, Kunlun Wanwei open source commercial large model, supports consumer-grade graphics card deployment

FPGA accelerator supports ChatGPT-like large language model innovation

65 billion parameters, training soared by 38%! The best practice of LLaMA basic large model reproduction is open source, and GitHub has won 30k stars

Breaking language barriers: Google releases the M4 translation model with 50 billion training parameters and supports 103 languages

DeepSpeed Chat: One-click RLHF training, make your ChatGPT-like 100 billion large model speed up and save money by 15 times

ChatGPT-like open source software, can developers use it?

Baichuan Intelligent released the first closed-source large model with 53 billion parameters, catching up with GPT-3.5 this year

3.6 trillion tokens, 340 billion parameters, details of Google's large model PaLM 2 exposed

Falcon with 180B parameters tops Hugging Face, surpassing Llama 2, claiming to be the best open source large model currently

[Study Notes] Summary of Research on Open Source Chinese Dialogue Pre-training Model

Falcon 180B is currently the most powerful open source model

Open source Chinese client based on Google Flutter, supports Android and iOS

Simple use of 6 open source software that supports Chinese speech recognition

Li Yunlong and Xie Erduo are professional escorts! ChatHaruhi explodes: supports 32 Chinese and foreign characters, open source 54,000 conversation data

js convert money into Chinese yuan units, million, billion, trillion

The most powerful large language model with 7 billion parameters so far: the open source and commercially available RedPajam 7B full version is released!

Huawei's latest large model is here! Pangu 3.0 came out, with a scale of 100 billion parameters and 3 trillion tokens, saying "do not write poetry but do things"

Goose plant open source pioneer, calculate the average daily volume of over 3.0 trillion effort to break the data wall

Falcon 180B: новое будущее LLM (производительность выше, чем у ChatGPT 3.5). Углубленный взгляд на крупнейшую в мире модель открытого языка, ее возможности и способы использования ее расширенных конфигураций.

70 billion parameters Llama 2 training accelerated by 195%! Data has become a key element to improve its effectiveness

GPT-4 parameters latest revelation 1.76 trillion parameters, 8 220 billion MoE models, convinced

The technology behind the open source large model BLOOM with hundreds of billions of parameters

Powerful like GPT-3, 175 billion parameters can't handle Chinese

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)