---
license: apache-2.0
---

## convert ggml-vicuna-7b-f16 to ggml-vicuna-7b-q4_0
Source: https://huggingface.co/chharlesonfire/ggml-vicuna-7b-f16

No unnecessary changes

## Usage:

1. Download llama.cpp from https://github.com/ggerganov/llama.cpp

2. make and run llama.cpp and choose model with ggml-vicuna-7b-q4_0.bin