Micheal Kinney

I had the same issue on both Windows 10 and 11 (different machines, both VS 2022). I think it's a environment variable issue or it it should have changed directories...

> > I had the same issue on both Windows 10 and 11 (different machines, both VS 2022). I think it's a environment variable issue or it it should have...

I'm curious if this will make much of a difference, I will be testing it shortly.. but I can confirm this works. It might just improve the resolution of my...

> I've been working on an API that's pretty stable now for my uses, it has 30m SRTM, 10m NED, and some other open datasets. > > Code: [ajnisbet/opentopodata](https://github.com/ajnisbet/opentopodata) Docs...

> @aliasfoxkde Would love to pick your brain. How do we connect? Working on hosting our own elevation API, starting with Open Elevation and replacing it with better US data....

Very cool but I think you might be bottlenecked by the API through web here. Alternatively, I took only the raw "gdal_interfaces.py" and stripped down the server.py file to get...

> Dropping this here for those who don't know: You can serve any model as an OpenAI API compatible API endpoint with Basaran: https://github.com/hyperonym/basaran > > "Basaran is an open-source...

> @MarkSchmidty yeah this has to happen eventually. for the embeddings: > > * https://www.tensorflow.org/hub/tutorials/semantic_similarity_with_tf_hub_universal_encoder > > another option is also no embeddings at all, after all you can do...

> Vicuna-13B and other 13B fine tunes in 4bit are only 8GB and even run purely on CPU at useful speeds. "Open Assistant LLaMA-13B" is also highly capable, similar to...

> For GPU, a [24GB Nvidia P40 is $200](https://www.ebay.com/sch/i.html?_from=R40&_trksid=p2380057.m570.l1313&_nkw=24GB+Nvidia+Tesla+P40&_sacat=0) and can support up to 33B parameters in 4bit at high speeds. Two $200 P40s can run 65B at fairly high...