Out of extreme frustration and hours spent on debugging conda environments, python compatability, un-installing and re-installing packages, I decided to purchase Google Colab Pro + I am so happy to not worry about the compute problems and that I can run many different LLM pipelines on different sessions at once :)

Excited to try many different prompts (Paper Plain prompt, 5th grade paraphase and define (a prompt Sebastian made), and coming up with different prompts related to medical text). Prompt engineering definitely feels a bit like a black hole… but so far Paper Plain seems to be pretty reliable

I’m enjoying getting my hands dirty with HuggingFace pipelines to run inference on REDPajama, ALPACA, FALCON, MEDALPACA, and more More generations to come…