WesselvanGils

Will there ever be a solution to this? I'm stuck with the same problem and seeing as this issues latest reply was from Mar, I'm hoping somone has found a...

I see, it's returning -1, that explains the IndexOutOfRange. Is this an issue with the model itself?

I'm not sure on this yet but, not having a newline token seems to be a commonality for embedding models. For nomic I tested F32, F16 and Q2_K, I then...

It could be this is intended behavoir. The models I've been testing are models for generating embeddings so it makes sense that they don't have a newline token as they...

I'm trying to make basically exactly this right now. I got the `BatchedExecutor` figured out recently but now trying to integrate RAG into that pipeline is proving difficult. I wouldn't...

I did actually manage to figure this out with `semantic memory`. I'll put a proper example for that version together tomorrow. The advantage of that over the solution above is...

```cs using LLama; using LLama.Common; using LLama.Native; using LLamaSharp.SemanticKernel.TextEmbedding; using Microsoft.SemanticKernel.Connectors.Sqlite; using Microsoft.SemanticKernel.Memory; using Microsoft.SemanticKernel.Text; using System.Text; // Initialize native library before anything else string llamaPath = Path.GetFullPath("/libllama.so"); NativeLibraryConfig.Instance.WithLibrary(llamaPath, null);...

Hi, I've been wanting to try this out myself but I can't get the example to work. After fiddeling around a bit I've gotten pretty far, my code now looks...

I've been experimenting with the `BatchedExecutor` for a bit now and I have a couple questions. Can we create conversations and prompt them in parallel? Can `BatchedExecutor.Infer()` be run in...

I got that figured out after a bit as well @AsakusaRinne but thanks for the advice nontheless. I managed to get a working iteration of it and thought I'd share...