ktransformers icon indicating copy to clipboard operation
ktransformers copied to clipboard

[Bug] 为什么 Qwen2-57B-GGUF 的chat结果是空白?

Open batmancn opened this issue 1 month ago • 3 comments

Checklist

  • [ ] 1. I have searched related issues but cannot get the expected help.
  • [ ] 2. The bug has not been fixed in the latest version.
  • [ ] 3. Please note that if the bug-related issue you submitted lacks corresponding environment info and a minimal reproducible demo, it will be challenging for us to reproduce and resolve the issue, reducing the likelihood of receiving feedback.
  • [ ] 4. If the issue you raised is not a bug but a question, please raise a discussion at https://github.com/kvcache-ai/ktransformers/discussions. Otherwise, it will be closed.
  • [ ] 5. To help the community, I will use Chinese/English or attach an Chinese/English translation if using another language. Non-Chinese/English content without translation may be closed.

Describe the bug

大家好,

我通过这个命令启动了大模型: python3 ktransformers/ktransformers/local_chat.py --model_path ./Qwen2-57B-A14B-Instruct --gguf_path Qwen2-57B-GGUF

然后进入到这个界面: Chat:

然后我输入了问题: 1+1=?

然后显示如下:

Chat: 1+1=? (下面不是空行,是很多空白)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            
prompt eval count:    23 token(s)
prompt eval duration: 1.0584766864776611s
prompt eval rate:     21.729340186544967 tokens/s
eval count:           1000 token(s)
eval duration:        102.8101806640625s
eval rate:            9.726663191727587 tokens/s
Chat:

这是为什么?是模型输出的问题?还是ktransformers编解码的问题?请问有谁用过这个模型吗?

Reproduction

python3  ktransformers/ktransformers/local_chat.py --model_path ./Qwen2-57B-A14B-Instruct --gguf_path Qwen2-57B-GGUF

Environment

Chat: 1+1=? (下面不是空行,是很多空白)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            
prompt eval count:    23 token(s)
prompt eval duration: 1.0584766864776611s
prompt eval rate:     21.729340186544967 tokens/s
eval count:           1000 token(s)
eval duration:        102.8101806640625s
eval rate:            9.726663191727587 tokens/s
Chat:

batmancn avatar Oct 28 '25 01:10 batmancn

另外请问一下,ktransformers的日志在哪里?能从日志中看到输出的是什么字符吗?

batmancn avatar Nov 02 '25 09:11 batmancn

好像是模型输出的问题,Qwen模型输出有这个问题,DeepSeek输出没这个问题。那Qwen模型输出为什么有这个问题?

batmancn avatar Nov 03 '25 08:11 batmancn

你好 我也是同样的问题 请问您解决了嘛 我也是DeepSeek输出没这个问题 使用Qwen2-57B-A14B-Instruct.Q4_K.gguf这个模型就有问题 输出全是空白 空格

YHCyhc20010606 avatar Nov 12 '25 03:11 YHCyhc20010606