Hacker Newsnew | past | comments | ask | show | jobs | submitlogin
Directly run and investigate Llama models locally (github.com/anordin95)
8 points by anordin95 10 months ago | hide | past | favorite | 1 comment


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.




Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: