Makes transformer script executable via cli

transform/ensure_gte_model.sh

@@ -1,16 +1,35 @@
 #!/usr/bin/env bash
 set -euo pipefail
 
-if [ -d "$GTE_MODEL_PATH" ] && find "$GTE_MODEL_PATH" -type f | grep -q .; then
+if [ -d "$GTE_MODEL_PATH" ] && [ -f "$GTE_MODEL_PATH/config.json" ]; then
     echo "GTE model already present at $GTE_MODEL_PATH"
     exit 0
 fi
 
-echo "Downloading GTE model to $GTE_MODEL_PATH"
+echo "Downloading GTE model $GTE_MODEL_ID to $GTE_MODEL_PATH"
 mkdir -p "$GTE_MODEL_PATH"
-curl -sL "https://huggingface.co/api/models/${GTE_MODEL_ID}" | jq -r '.siblings[].rfilename' | while read -r file; do
-    target="${GTE_MODEL_PATH}/${file}"
-    mkdir -p "$(dirname "$target")"
-    echo "Downloading ${file}"
-    curl -sL "https://huggingface.co/${GTE_MODEL_ID}/resolve/main/${file}" -o "$target"
-done
+
+# Use Python with huggingface_hub for reliable model downloading
+python3 << 'EOF'
+import os
+from huggingface_hub import snapshot_download
+
+model_id = os.environ.get('GTE_MODEL_ID')
+model_path = os.environ.get('GTE_MODEL_PATH')
+
+if not model_id or not model_path:
+    raise ValueError(f"GTE_MODEL_ID and GTE_MODEL_PATH environment variables must be set")
+
+try:
+    print(f"Downloading model {model_id} to {model_path}")
+    snapshot_download(
+        repo_id=model_id,
+        cache_dir=None,  # Don't use cache, download directly
+        local_dir=model_path,
+        local_dir_use_symlinks=False  # Don't use symlinks, copy files
+    )
+    print(f"Successfully downloaded GTE model to {model_path}")
+except Exception as e:
+    print(f"Error downloading GTE model: {e}")
+    exit(1)
+EOF