Upload model_usage.md with huggingface_hub

model_usage.md

@@ -30,10 +30,10 @@ sys.path.append(os.path.dirname(spa_file))
 # Now you can import from the downloaded files
 from spa_hf import load_spa_model
 
-# Load the SPA model with your preferred base model
+# Load SPA with just the base model, ignoring any saved configurations
 spa_model = load_spa_model(
-    model_name=repo_id,
-    base_model_name="meta-llama/Llama-3.1-8B-Instruct",  # Use any model you prefer
+    model_name=None,  # Skip loading from Hub
+    base_model_name="Qwen/Qwen3-0.6B",  # Use your preferred base model
     device_map="auto"  # Use "cpu" if you don't have a GPU
 )