Fix adapter path and repopulate model files for HF Spaces deployment

app.py

@@ -6,7 +6,7 @@ from mlx_lm.sample_utils import make_sampler
 print("Loading fine-tuned model...")
 model, tokenizer = mlx_lm.load(
     'mlx-community/Llama-3.2-3B-Instruct-4bit',
-    adapter_path='./models/llama3.2-3b-quotes-lora-mlx'
+    adapter_path='./models'
 )
 print("✅ Model loaded successfully!")