39 lines
1.4 KiB
Bash
Executable File
39 lines
1.4 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# download-model.sh — Download the quantized ONNX model for client-side semantic search.
|
|
#
|
|
# Downloads Xenova/all-MiniLM-L6-v2 (quantized ONNX, ~22 MB total) from HuggingFace
|
|
# into static/models/all-MiniLM-L6-v2/ so it can be served same-origin, keeping the
|
|
# nginx CSP to 'self' for connect-src.
|
|
#
|
|
# Run once before deploying. Files are gitignored (binary artifacts).
|
|
# Re-running is safe — existing files are skipped.
|
|
|
|
set -euo pipefail
|
|
|
|
REPO_ROOT="$(cd "$(dirname "$0")/.." && pwd)"
|
|
MODEL_DIR="$REPO_ROOT/static/models/all-MiniLM-L6-v2"
|
|
BASE_URL="https://huggingface.co/Xenova/all-MiniLM-L6-v2/resolve/main"
|
|
|
|
mkdir -p "$MODEL_DIR/onnx"
|
|
|
|
fetch() {
|
|
local src="$1" dst="$2"
|
|
if [ -f "$dst" ]; then
|
|
echo " skip $src (already present)"
|
|
return
|
|
fi
|
|
echo " fetch $src"
|
|
curl -fsSL --progress-bar "$BASE_URL/$src" -o "$dst"
|
|
}
|
|
|
|
echo "Downloading all-MiniLM-L6-v2 to $MODEL_DIR ..."
|
|
|
|
fetch "config.json" "$MODEL_DIR/config.json"
|
|
fetch "tokenizer.json" "$MODEL_DIR/tokenizer.json"
|
|
fetch "tokenizer_config.json" "$MODEL_DIR/tokenizer_config.json"
|
|
fetch "special_tokens_map.json" "$MODEL_DIR/special_tokens_map.json"
|
|
fetch "onnx/model_quantized.onnx" "$MODEL_DIR/onnx/model_quantized.onnx"
|
|
|
|
echo "Done. static/models/all-MiniLM-L6-v2/ is ready."
|
|
echo "Run 'make build' to copy the model files into _site/."
|