rabilrbl/llamafile-builder

A simple github actions script to build a llamafile and uploads to huggingface

32
/ 100
Emerging

This tool helps developers package large language models (LLMs) into a single, executable file called a 'llamafile'. You provide a URL to an existing LLM model file (specifically a GGUF file) and specify a Hugging Face repository. The process then creates the llamafile and uploads it to your designated repository, making it easier to distribute and run LLMs without complex setups.

No commits in the last 6 months.

Use this if you are a developer looking for a streamlined way to create and share single-file, portable LLMs from existing GGUF models.

Not ideal if you need to train or fine-tune an LLM, or if you are not comfortable working with GitHub Actions and Hugging Face repositories.

LLM deployment Model distribution Developer workflow AI infrastructure
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 18 / 25

How are scores calculated?

Stars

17

Forks

12

Language

Python

License

Last pushed

Jan 11, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/rabilrbl/llamafile-builder"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.