-
Notifications
You must be signed in to change notification settings - Fork 1.5k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Bug][ChatDB]Using qwen-1.5-14b-chat, there are more than a dozen tables in the library, but when asking for table information, it says that there are only four tables in the library. Is it because the number of model tokens is not enough or is there another problem #1462
Comments
我使用通义千问-Turbo,返回的也只有4张表,但库里有很多张表 |
Please use the |
@yyhhyyyyyy ,thank you |
@yyhhyyyyyy ,微信二维码还有吗,之前的过期了 |
俺也想要 |
@guiniao @Dingzhen778 hi,the WeChat QR code has been updated. |
@yyhhyyyyyy 可以发我一个吗?
|
我想请教一下,我直接在我的笔记本Docker环境中跑这个,是必须需要显卡吗?我无显卡跑不起来 |
@mengdahuang hi,Yes, currently the Docker image we have packaged only supports the GPU version; we haven't included a non-GPU version yet, but it will be updated later. You can keep an eye out for that. |
@yyhhyyyyyy hi, thank you so much for your kindly reply, will try source code install later. BTW, where i can got the updated WeChat QR code ? :) |
|
This issue has been marked as |
Search before asking
Operating system information
Linux
Python version information
3.10
DB-GPT version
main
Related scenes
Installation Information
Installation From Source
Docker Installation
Docker Compose Installation
Cluster Installation
AutoDL Image
Other
Device information
gpu count:2
memory:24G(每个)
Models information
LLM:Qwen1.5-14B-Chat
EMBEDDING_MODEL:m3e-large
What happened
查询库中表信息,返回的数据不对,使用的qwen-1.5-14b-chat,是模型性能不够,token不够吗
What you expected to happen
返回的结果,表数量不对,不知道是模型性能问题还是其他原因
How to reproduce
返回的结果,表数量不对,不知道是模型性能问题还是其他原因
Additional context
No response
Are you willing to submit PR?
The text was updated successfully, but these errors were encountered: