Update app.py

app.py

@@ -6,13 +6,12 @@ from transformers import pipeline
 print(f"GPU available: {torch.cuda.is_available()}")
 print(f"GPU name: {torch.cuda.get_device_name(0) if torch.cuda.is_available() else 'None'}")
 
-# Initialize pipeline with GPU acceleration
+# Initialize pipeline WITHOUT 4-bit quantization
 pipe = pipeline(
     "text-generation",
     model="agentica-org/DeepCoder-14B-Preview",
     device="cuda" if torch.cuda.is_available() else "cpu",
     torch_dtype=torch.bfloat16 if torch.cuda.is_available() else torch.float32,
-    model_kwargs={"load_in_4bit": True}  # Quantization for memory efficiency
 )
 
 def chat(message, history):