gistfile1.txt

import os
import json
import numpy as np
import coremltools as ct
from transformers import CLIPTokenizer

# 1. Load labels
with open("stats.txt", "r") as f:
    categories = [line.strip() for line in f if line.strip()]

# 2. Load CLIP-compatible tokenizer
tokenizer = CLIPTokenizer.from_pretrained("openai/clip-vit-base-patch32")

# 3. Process embeddings 
model_path = os.path.join(
    "mobileclip_blt_text.mlpackage",
    "Data",
    "com.apple.CoreML",
    "model.mlmodel"
)

if not os.path.isfile(model_path):
    print(f"❌ model.mlmodel not found for {variant}")
    continue

print(f"📦 Loading model for {variant}: {model_path}")
model = ct.models.MLModel(model_path)

entries = []