Jonathan Yankovich

:clap: Thank you @iRanadheer - Information on how to integrate local models with langchain is sparse. This little tidbit is helpful. If you know of any repos that provide toy...

@lukestanley Thanks for asking! I saw the LlamaCpp example, but my understanding is that the -Cpp interface/classes are very different from huggingface/pt/safetensors. I agree that Cpp is more accessible for...

Getting Guidance to work with Exllama is a pretty significant step, since getting structured content out of an LLM is one of the biggest hurdles to application development. (That i...

Posting for visibility; This issue with deleting files via NFS happens to me consistently on Unraid 6.12.8 (latest) which as I understand it uses libfuse. There are a number of...

I don't have access to the unraid source, but if I can test on my running Unraid instance, I am happy to. I'll need some pointers on where to look...

@trapexit Whew, okay... thanks for suggesting this as a way to make some progress on this issue. I may be able to do that with a proxmox VM, though I...

So here's an interesting developemnt - After discussing the issue with ChatGPT, I tried changing my NFS mount in fstab from: ``` 10.1.1.11:/mnt/user/main /mnt/main nfs4 rw,sync,hard,intr,noatime,nolock 0 0 ``` to...

Thanks for the info @bsbernd ! Just now I encountered the error using the same mount args as above: ``` 10.1.1.11:/mnt/user/main /mnt/main nfs4 rw,sync,hard,noatime,actimeo=1 0 0 ``` So, this still...

I'd love to see some sort of software-only "willow" that would run as a daemon under MacOS/Ubuntu/Window, and act as a bridge to willow-inference-server, so one could use an onboard...

@sparkydave1981 What functionality would you be looking to enable by providing Home Assistant integration? If this were done, my hope would be that it would be decoupled from willow-inference-server. Just...