Update app.py

Comment out HQQ config...

app.py

@@ -5,7 +5,7 @@ import gradio as gr
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM, HqqConfig
 
-quant_config = HqqConfig(nbits=8, group_size=64)
+# quant_config = HqqConfig(nbits=8, group_size=64)
 
 MODEL_ID = "HuggingFaceTB/SmolLM3-3B"
 DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
@@ -20,7 +20,7 @@ model =\
                         MODEL_ID, 
                         torch_dtype=torch.float16, 
                         # device_map="cuda", 
-                        quantization_config=quant_config
+                        # quantization_config=quant_config
         ).to(DEVICE)
 
 #gc.collect()