Thousand Questions on Tongyiteamup to dateThe Qwen1.5-32B model series was released, which includes the Qwen1.5-32B and Qwen1.5-32B-Chat.
These models are basically the same as the previous Qwen1.5 series in terms of model architecture, but the number of parameters is reduced to 32B, aiming to provide a more efficient and affordable solution. Qwen1.5-32B performs well in basic language model capabilities, conversation capabilities, and multilingual capabilities, and is comparable to the currentOptimalCompared with the 30B model, the performance is excellent.
This release aims to address the weak capabilities of the 14B model in agent scenarios and the high inference cost of the 72B model.
Qwen1.5-32B:
https://modelscope.cn/models/qwen/Qwen1.5-32B
Qwen1.5-32B-Chat:
https://modelscope.cn/models/qwen/Qwen1.5-32B-Chat
Qwen1.5-32B-Chat-GPTQ-Int4:
https://modelscope.cn/models/qwen/Qwen1.5-32B-Chat-GPTQ-Int4
Qwen1.5-32B-Chat-AWQ:
https://modelscope.cn/models/qwen/Qwen1.5-32B-Chat-AWQ
Qwen1.5-32B-Chat-GGUF:
https://modelscope.cn/models/qwen/Qwen1.5-32B-Chat-GGUF