Directly run and investigate Llama models locally

(github.com)

8 points | by anordin95 3 days ago ago

1 comments

  • anordin95 3 days ago ago

    There are other popular ways to invoke these models, such as Ollama and Hugging-Face's general API package: transformers, but those hide the interesting details behind an API. I want to peel back the layers, poke, prod, understand and gain insight into these models and help you do the same.