Update app.py

Revert quantization until I can investigate the Exceptions it is raising at generate() time ...

app.py

@@ -12,8 +12,8 @@ tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
 
 model = AutoModelForCausalLM.from_pretrained(
     MODEL_ID,
-    load_in_8bit=True,  # or try load_in_4bit=True
-    device_map=DEVICE
+    # load_in_8bit=True,  # or try load_in_4bit=True
+    # device_map=DEVICE
 )
 
 #########