llamafile-creation.sh

#!/bin/sh

# Pull both the model folder and llama.cpp (for the conversion script)
git submodule update --init

# Convert from safetensor to gguf
# (Assuming llama.cpp is in the next folder)
./llama.cpp/convert.py maykeye_tinyllama --metadata maykeye_tinyllama-metadata.json

# Copy the generated gguf to this folder
cp maykeye_tinyllama/TinyLLama-v0-5M-F16.gguf TinyLLama-v0-5M-F16.gguf

# Get the llamafile engine
cp /usr/local/bin/llamafile TinyLLama-v0-5M-F16.llamafile

# Create an .args file with settings defaults
cat >.args <<EOF
-m
TinyLLama-v0-5M-F16.gguf
EOF

# Combine
zipalign -j0 \
  TinyLLama-v0-5M-F16.llamafile \
  TinyLLama-v0-5M-F16.gguf \
  .args

# Test
./TinyLLama-v0-5M-F16.llamafile