Jake Luciani
Jake Luciani
So I tried doing this and the first issue was I needed to upgrade the plugin to run on 2024.2+: Java 21. This seemed to get me further but then...
Thanks for this. I wonder if the KV cache should be marked ephemeral when the model is created? Otherwise you can never keep the cache around long term (say you...
> Based on my understanding of the [LangChain4j chat memory documentation](https://github.com/langchain4j/langchain4j/blob/main/docs/docs/tutorials/chat-memory.md), there is no default persistence. Correct, in this case it would always be ephemeral. But for Jlama I want...
Hi, there is a bug with the build recently, I have a fix in #150 that should be merging soon
I'll need to try these out and see why it doesn't work. It should work
Hello! Looks like you reached the context length of the model. Which can happen for that one as it goes off the rails sometimes (even at 0.2). I can/should add...
In the meantime set a lower maxTokens
The architecture looks quite different so it may take some time for me to figure it out (on top of other priorities)
Hi, which model are you using? Often the small quantize ones have trouble with tool calling like this.