كوين كيو‌وِن Qwen

Qwen
Logo of Qwen.png
المطوّرAlibaba Cloud
الإطلاق المبدئيأبريل 2023; 1 year ago (2023-04
الإصدار المستقر
2.5-Max / يناير 2025; 2 months ago (2025-01
المستودعgithub.com/QwenLM/Qwen
مكتوب بلغةPython
نظام التشغيل
النوعChatbot
الرخصة
الموقع الإلكتروني

كوين/كيو‌وِن Qwen (ويُدعى أيضاً Tongyi Qianwen، Chinese: 通义千问) هي عائلة من نماذج اللغة الكبيرة طوّرتها علي بابا. في يوليو 2024، كان ترتيبها الأعلى بين نماذج اللغة الصينية في بعض المعايير والثالثة عالمياً خلف النماذج العليا لكل من أنثروپيك و OpenAI.[1]

النماذج

Alibaba first launched a beta of Qwen in April 2023 under the name Tongyi Qianwen.[2] The model was based on the LLM Llama developed by Meta AI, with various modifications.[3] It was publicly released in September 2023 after receiving approval from the Chinese government.[4] In December 2023 it released its 72B and 1.8B models as open source, while Qwen 7B was open sourced in August.[5][6]

In June 2024 Alibaba launched Qwen 2 and in September it released some of its models as open source, while keeping its most advanced models proprietary.[7][8] Qwen 2 employs a mixture of experts.[9]

In November 2024, QwQ-32B-Preview, a model focusing on reasoning similar to OpenAI's o1 was released under the Apache 2.0 License, although only the weights were released, not the dataset or training method.[10][11] QwQ has a 32,000 token context length and performs better than o1 on some benchmarks.[12]

The Qwen-Vl series is a line of visual language models that combines a vision transformer with a LLM.[3][13] Alibaba released Qwen-VL2 with variants of 2 billion and 7 billion parameters.[14][15] Qwen-vl-max is Alibaba's flagship vision model as of 2024 and is sold by Alibaba Cloud at a cost of US$0.00041 per thousand input tokens.[16]

Alibaba has released several other model types such as Qwen-Audio and Qwen2-Math.[17] In total, it has released more than 100 models as open source, with its models having been downloaded more than 40 million times.[8][18] Fine-tuned versions of Qwen have been developed by enthusiasts, such as "Liberated Qwen", developed by San Francisco-based Abacus AI, which is a version that responds to any user request without content restrictions.[19]

In January 2025, Alibaba launched Qwen 2.5-Max, its latest and most powerful model to date.[20] According to a blog post from Alibaba, Qwen 2.5-Max outperforms other foundation models such as GPT-4o, DeepSeek-V3, and Llama-3.1-405B in key benchmarks.[21]


المراجع

  1. ^ Jiang, Ben (11 July 2024). "Alibaba's open-source AI model tops Chinese rivals, ranks 3rd globally". South China Morning Post (in الإنجليزية).
  2. ^ Chiang, Sheila (11 April 2023). "Alibaba to roll out its rival to ChatGPT across all its products". CNBC (in الإنجليزية).
  3. ^ أ ب Bai, Jinze; et al. (28 Sep 2023). "Qwen Technical Report". arXiv:2309.16609 [cs.CL].
  4. ^ Jiang, Ben (13 September 2023). "Alibaba opens Tongyi Qianwen model to public as new CEO embraces AI". South China Morning Post (in الإنجليزية).
  5. ^ Fan, Feifei (2023-12-01). "Alibaba unveils new Tongyi Qianwen AI language model". global.chinadaily.com.cn.
  6. ^ Ye, Josh (August 3, 2023). "Alibaba rolls out open-sourced AI model to take on Meta's Llama 2". reuters.
  7. ^ Jiang, Ben (7 June 2024). "Alibaba says new AI model Qwen2 bests Meta's Llama 3 in tasks like maths and coding". South China Morning Post (in الإنجليزية).
  8. ^ أ ب Kharpal, Arjun (19 September 2024). "China's Alibaba launches over 100 new open-source AI models, releases text-to-video generation tool". CNBC (in الإنجليزية).
  9. ^ Yang, An; et al. (10 Sep 2024). "Qwen2 Technical Report". arXiv:2407.10671 [cs.CL].
  10. ^ Dickson, Ben (29 November 2024). "Alibaba releases Qwen with Questions, an open reasoning model that beats o1-preview". VentureBeat.
  11. ^ 故渊 (2024-11-28). "阿里通义千问 QwQ 登场：开源 AI 推理新王，MATH 测试超 OpenAI o1 模型 - IT之家". www.ithome.com.
  12. ^ Wiggers, Kyle (27 November 2024). "Alibaba releases an 'open' challenger to OpenAI's o1 reasoning model". TechCrunch.
  13. ^ Browne, Ryan (31 December 2024). "Alibaba slashes prices on large language models by up to 85% as China AI rivalry heats up". CNBC (in الإنجليزية).
  14. ^ 沛霖 (2024-08-30). "阿里通义千问推出 Qwen2-VL：开源 2B / 7B 参数 AI 大模型，处理任意分辨率图像无需分割成块". ithome.com.
  15. ^ Wang, Peng; Bai, Shuai; Tan, Sinan; Wang, Shijie; Fan, Zhihao; Bai, Jinze; Chen, Keqin; Liu, Xuejing; Wang, Jialin; Ge, Wenbin; Fan, Yang; Dang, Kai; Du, Mengfei; Ren, Xuancheng; Men, Rui; Liu, Dayiheng; Zhou, Chang; Zhou, Jingren; Lin, Junyang (September 18, 2024). "Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution". Cs.CV. arXiv:2409.12191.
  16. ^ Jiang, Ben (31 December 2024). "Alibaba Cloud cuts AI visual model price by 85% on last day of the year". South China Morning Post (in الإنجليزية).
  17. ^ Franzen, Carl (8 August 2024). "Alibaba claims no. 1 spot in AI math models with Qwen2-Math". VentureBeat.
  18. ^ "Alibaba accelerates AI push by releasing new open-source models, text-to-video". Reuters. September 19, 2024.
  19. ^ Mims, Christopher (April 19, 2024). "Here Come the Anti-Woke AIs". WSJ.
  20. ^ Brunner, Nathan (29 January 2025). "Qwen 2.5-Max - Latest Statistics and Facts". boterview (in الإنجليزية).
  21. ^ "Qwen2.5-Max: Exploring the Intelligence of Large-scale MoE Model". Github (in الإنجليزية). 29 January 2025.

قالب:Generative AI chatbots قالب:Generative AI قالب:Artificial intelligence navbox

تمّ الاسترجاع من "https://www.marefa.org/w/index.php?title=Qwen&oldid=4084507"