I’ve playing with a lot of models around 7B but I’m now prototyping something that would be fine with a 1B model I think, but there’s just Phi-1.5 that I’ve seen of this size, and I haven’t seen a way to run it efficiently so far. llama.cpp has still not implemented it for instance.
Anyone has an idea of what to use?
I would still give it a try— it’s misleading to think these coding models are only good at that, being good at coding actually has shown to improve its scores across multiple benchmarks.