abacaj/Replit-v2-CodeInstruct-3B-ggml

This is a ggml quantized version of Replit-v2-CodeInstruct-3B. Quantized to 4bit -> q4_1. To run inference you can use ggml directly or ctransformers.

• —Memory usage of model: 2GB~
• —Repo to run the model using ctransformers: https://github.com/abacaj/replit-3B-inference