Qwen
/

CodeQwen1.5-7B-Chat-GGUF

Text Generation

Inference Endpoints

Model card Files Files and versions Community

Resources

View closed (1)

我在ollama上部署了codeqwen-1_5-7b-chat-q5_0.gguf可是对话很奇怪，这个是为什么，有什么解决办法吗

#4 opened 7 months ago by

broken output when gpu enable

#3 opened 7 months ago by

Using llama.cpp server, responses always end with <|im_end|>

#2 opened 8 months ago by