Replies: 2 comments 4 replies
-
|
It should be, it's just not configured. |
Beta Was this translation helpful? Give feedback.
-
|
so i have to open the llm_config.yaml and change "/api/v1/generate" to "/v1/chat/completions" ? or where do you mean to change it? |
Beta Was this translation helpful? Give feedback.
-
|
Yes, but just to "completion" according to that doc. |
Beta Was this translation helpful? Give feedback.
-
|
I wrote /completion as endpoint and didnt work i will try only with completion |
Beta Was this translation helpful? Give feedback.
-
|
I'm not familiar with llama.cpp, I'm just guessing from the documentation. But I see no reason why it shouldn't work. |
Beta Was this translation helpful? Give feedback.
-
|
Not sure if you solved this, but I just added a guide to the wiki: https://github.com/neph1/LlamaTale/wiki/Configuring-llama.cpp-server |
Beta Was this translation helpful? Give feedback.
-
so i would like to know if is possible to use it with llama.cpp using ./server and listening port 5001, i tried and didnt work
Beta Was this translation helpful? Give feedback.
All reactions