Alex "mcmonkey" Goodwin

This is a page for issues related to the StableLM project, view the readme to learn how to test-drive the model.

ChatGPT randomizes too. There's even a regenerate button on ChatGPT's site to get a different random answer. (It does tend to be more often right, though, of course - but...

You can load the model in 16-bit or 8-bit. If you know how to work with python, it shouldn't be too hard. If not, There are projects like https://github.com/oobabooga/text-generation-webui that...

(I am not a lawyer, this is not legal advice, consult a real lawyer before making decisions, this is just my personal thought) Scale matters a lot when considering dataset...

@zoobab View the readme @ https://github.com/Stability-AI/StableLM#models for dataset info. More detail will be published soon. I don't think a ten gig+ model file is fit to be packaged natively into...

The GGML project, for running LLMs on CPUs (including specifically mac support!) has an initial example project that can run StableLM: https://github.com/ggerganov/ggml/tree/master/examples/stablelm There's also https://huggingface.co/cakewalk/ggml-q4_0-stablelm-tuned-alpha-7b/tree/main which supposedly works in llama.cpp

There's actually also a related but separate issue raised with this code (irrelevant to the PR, same issue before/after): If beam search is used, this is designed such that *any...

There's a bit of a misunderstanding, allow me to clarify: `this release under non-commercial license to get feedback and create commercial and free StableIF` This means: the initial release of...

I believe using external projects like GGML aka `llama.cpp`, apple silicon is supported for StableLM models.

That's... hard to answer, as I can't see your screen or what you're doing. Can you add some more detail? How are you running it, what outputs are you getting,...