Devis Lucato

About LLamaSharp, could you point me to how to count the tokens for a given string? is there some example?

I started a draft to integrate LlamaSharp into KernelMemory here https://github.com/microsoft/kernel-memory/pull/192 I'm using `llama-2-7b-chat.Q2_K.gguf` for my tests. A few questions: * which packages should I use/import? assume the user should...

Update: LLamaSharp 0.8.1 is now integrated into KernelMemory, here's an example: https://github.com/microsoft/kernel-memory/blob/main/examples/105-dotnet-serverless-llamasharp/Program.cs There's probably some work to do for users, e.g. customizing prompts for LLama and identifying which model works...

@AsakusaRinne I would take the opportunity to **thank you all for LlamaSharp**, making it so straightforward to integrate Llama into SK and KM. Before removing KM from LlamaSharp, I'd just...

hi @Aya-S, you mean a method to go from a list of token IDs to a string? could you elaborate about the scenario where this could be useful? Some tokens...

thank you @kayhantolga this is great! :-) FYI I'm also porting the tokenizer into [Semantic Kernel](https://github.com/microsoft/semantic-kernel) ("SK"), and I will take these improvements over there too, perfect timing. As a...

@kayhantolga I tried the changes with a single big file and I could not see perf changes, so looks like the difference is only about the timing when the cache...

thanks! I'll look into it

looks like OpenAI is retiring Codex. I need to find out if Azure will offer it

hi @rmelilloii great to hear the solution could help! KM should totally work fine in Kubernetes. I would try first with the docker image mentioned in the main README. Configuration...