In addition to Weibo, there is also WeChat
Please pay attention
WeChat public account
Shulou
2025-02-28 Update From: SLTechnology News&Howtos shulou NAV: SLTechnology News&Howtos > IT Information >
Share
Shulou(Shulou.com)11/24 Report--
CTOnews.com Sept. 25 news, Aliyun today announced the open source Tongyi Qianwen 14 billion parameter model Qwen-14B and its dialogue model Qwen-14B-Chat, free for commercial use.
CTOnews.com Note: Aliyun has previously opened up the 7 billion parameter model Qwen-7B, with more than 1 million downloads in more than a month.
According to the data given by Aliyun, Qwen-14B surpasses the same scale model in a number of authoritative evaluations, and some indicators are even close to Llama2-70B.
According to reports, Qwen-14B is a high-performance open source model that supports multiple languages, with overall training data of more than 3 trillion Token, stronger reasoning, cognitive, planning and memory capabilities, and a maximum context window length of 8k.
On the other hand, Qwen-14B-Chat is a dialogue model obtained by fine SFT on the pedestal model, which can bring more accurate content, more in line with human preferences, and has an expansion in the imagination and richness of content creation.
From today, users can download the model directly from Ali Muda community, and they can also access and call Qwen-14B and Qwen-14B-Chat through Ali Yunlingji platform.
Zhou Jingren, CTO of Aliyun, said that Aliyun will continue to embrace open source and promote the ecological construction of China's big model. Aliyun firmly believes in the power of open source and takes the lead in self-development of large models, hoping to make large model technology reach small and medium-sized enterprises and individual developers more quickly.
Model zero code creation space experience address: https://modelscope.cn/stud/qwen/Qwen-14B-Chat-Demo environment configuration and installation python 3.8or above
Pytorch version 1.12 and above, version 2.0 and above is recommended
CUDA 11.4 or above is recommended (GPU users should consider this option)
Use steps Note: run under the environment configuration of PAI-DSW (can be run on a single card, the minimum requirement for video memory is 11G).
Qwen-14B-Chat model links:
Https://modelscope.cn/models/qwen/Qwen-14B-ChatQwen-14B model links:
Https://modelscope.cn/models/qwen/Qwen-14BQwen-14B-Chat-Int4 model links:
The https://www.modelscope.cn/models/qwen/Qwen-14B-Chat-Int4 community supports downloading the model's repo directly:
From modelscope.hub.snapshot_download import snapshot_download
Model_dir = snapshot_download ('qwen/Qwen-14B-Chat',' v1.0.0')
Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.
Views: 0
*The comments in the above article only represent the author's personal views and do not represent the views and positions of this website. If you have more insights, please feel free to contribute and share.
Continue with the installation of the previous hadoop.First, install zookooper1. Decompress zookoope
"Every 5-10 years, there's a rare product, a really special, very unusual product that's the most un
© 2024 shulou.com SLNews company. All rights reserved.