Tongyi Qianwen's open-source 32 billion parameter model has achieved full open-source for 7 major language models
芊芊551
发表于 2024-4-7 17:04:49
165
0
0
Alibaba Cloud's Tongyi Qianwen open-source 32 billion parameter model Qwen1.5-32B can balance performance, efficiency, and memory usage to the greatest extent possible, providing enterprises and developers with a more cost-effective model choice. At present, Tongyi Qianwen has opened up 7 major language models, with a cumulative download volume exceeding 3 million in open source communities at home and abroad.
Tongyi Qianwen has previously opened up six large language models with parameters of 500 million, 1.8 billion, 4 billion, 7 billion, 14 billion, and 72 billion, all of which have been upgraded to version 1.5. Among them, several small-sized models can be easily deployed on the end side, while the 72 billion parameter model has industry-leading performance and has repeatedly appeared on models lists such as HuggingFace. This open-source 32 billion parameter model will achieve a more ideal balance between performance, efficiency, and memory usage. For example, compared to the 14B model, the 32B model has stronger capabilities in intelligent agent scenarios; Compared to 72B, 32B has lower inference costs. The Tongyi Qianwen team hopes that the 32B open source model can provide better solutions for downstream applications.
In terms of basic capabilities, the 32 billion parameter model of Tongyi Qianwen has performed well in multiple evaluations such as MMLU, GSM8K, HumanEval, BBH, etc. Its performance is close to that of Tongyi Qianwen's 72 billion parameter model, far exceeding other 30 billion parameter models.
In terms of the Chat model, the Qwen1.5-32B-Chat model scored over 8 points in the MT Bench evaluation, and the gap between it and Qwen1.5-72B-Chat is relatively small.
In terms of multilingual abilities, the Tongyi Qianwen team selected 12 languages including Arabic, Spanish, French, Japanese, Korean, etc., and conducted assessments in multiple fields such as exams, comprehension, mathematics, and translation. The multilingual ability of Qwen1.5-32B is only slightly inferior to the 72 billion parameter model of Tongyi Qianwen.
CandyLake.com 系信息发布平台,仅提供信息存储空间服务。
声明:该文观点仅代表作者本人,本文不代表CandyLake.com立场,且不构成建议,请谨慎对待。
声明:该文观点仅代表作者本人,本文不代表CandyLake.com立场,且不构成建议,请谨慎对待。
猜你喜欢
- NIO: NOMI GPT model has exceeded 10 million chat interactions
- Google releases Gemma 2 open-source AI model
- ERNIE Bot calls 500 million model manufacturers every day, and the ecological competition is intense
- Baidu Robin Lee: The big model without application is worthless
- 2024 World Artificial Intelligence Conference | Robin Lee: Commercial closed source model is the best
- Robin Lee speaks! "Commercial closed source models are the most effective"
- Robin Lee's harsh words: the basic model without application is worthless regardless of whether it is opened or closed
- Baidu announces the free opening of the Wenxin Intelligent Agent Platform's Wenxin Big Model 4.0
- Toyota has completed its investigation into the model certification incident and no new violations have been found
-
21世纪经济报道记者韩利明上海报道当地时间7月8日,礼来(NYSE:LLY)宣布将以每股57美元的现金,收购Morphic的所有流通股(总计约32亿美元),以获得治疗炎症性肠病(IBD)和其他慢性疾病的实验性疗法,拓展免疫 ...
- 浪無月
- 昨天 18:13
- 支持
- 反对
- 回复
- 收藏
-
记者今日获悉,金融壹账通近日成功签约广州农村商业银行资产配置系统项目。据了解,金融壹账通将助力广州农村商业银行推进其财富管理业务的数字化转型,为全行财富客户提供专业化、场景化、个性化的精准服务,推 ...
- dongtianya
- 前天 19:08
- 支持
- 反对
- 回复
- 收藏
-
本报讯 (记者李冰)7月8日,在支付宝开放日上,支付宝宣布升级条码支付体验,推出“支付宝碰一下”,用户无需展示付款码,解锁手机碰一下商家收款设备,最快一步完成支付。据介绍,“碰一下”和“扫一下”都属 ...
- WJ1127H
- 前天 20:17
- 支持
- 反对
- 回复
- 收藏
-
7月8日,在支付宝开放日上,支付宝宣布升级条码支付体验,推出“支付宝碰一下”,用户无需展示付款码,解锁手机碰一下商家收款设备,最快一步完成支付。 碰一碰支付有很多优势 支付宝“碰一下”最快3 ...
- yearn1985
- 前天 17:14
- 支持
- 反对
- 回复
- 收藏