Cody Snider

@chrisohaver no response back from @hawell . at the moment, those docs are pointing to a plugin repo that doesn't compile. might be worth forking to the coredns org?

I'll volunteer. Maintainer or not, if someone else gets the job and wants to toss me a few bug tickets here and there, go for it. I've used this library...

@arnavsinghvi11 there's a new PR up as a continuation of this effort. it includes the snippet used to test against openhermes with llamacpp: https://github.com/stanfordnlp/dspy/pull/862

@randerzander I'm using it successfully in production with llama 3 (not an instruct variant, though) with typed output: ```python llm = Llama.from_pretrained( repo_id="QuantFactory/Meta-Llama-3-8B-GGUF", filename="Meta-Llama-3-8B.Q5_K_M.gguf", n_ctx=8192, n_gpu_layers=-1, verbose=False ) lm =...

This isn't the A1111 repository. Please keep the GUI cancer limited to the GUI repos.

Thanks, buddy. I'll pop in there tomorrow night when I get back onto this project. I've actually got the full set of APIs running on separate containers and orchestrated under...

Same for debian 10 with docker, rollback to 2.9.22 fixed it.