# Clone repo
git clone https://github.com/ggerganov/llama.cpp
cd llama.cpp

# Build
mkdir build
cd build
cmake ..
cmake --build . --config Release
cd ..

# Download model
export MODEL=llama-2-13b-chat.ggmlv3.q4_0.bin
if [ ! -f models/${MODEL} ]; then
curl -L "https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/resolve/main/${MODEL}" -o models/${MODEL}
fi

# Set prompt
PROMPT="Hello! How are you?"

# Run in interactive mode
./build/bin/main -m ./models/llama-2-13b-chat.ggmlv3.q4_0.bin \
--color \
--ctx_size 2048 \
-n -1 \
-ins -b 256 \
--top_k 10000 \
--temp 0.2 \
--repeat_penalty 1.1 \
-t 8