eosphoros
Replies: 1 comment 1 reply
-
|
The current performance of my use of llama-2-13b is quite impressive. The main challenge lies in how to extract the desired data from the vector database. Currently, this aspect is not well achieved in db-gpt. |
Beta Was this translation helpful? Give feedback.
1 reply
-
|
Of course, varying individual needs contribute to this, but speaking for my own requirements, I need to make adjustments to the vector database. |
Beta Was this translation helpful? Give feedback.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
How to evaluate the performance of different models in DB-GPT KBQA？
Beta Was this translation helpful? Give feedback.
All reactions