Update app.py

app.py

@@ -44,15 +44,15 @@ class SQLGEN(Base):
 
         
 model_id = "alibidaran/Gemma2_SQLGEN"
-
-bnb_config = BitsAndBytesConfig(
-    load_in_4bit=True,
-    bnb_4bit_quant_type="nf4",
-    bnb_4bit_compute_dtype=torch.bfloat16
-)
+#bnb_config for GPU usage 
+#bnb_config = BitsAndBytesConfig(
+ #   load_in_4bit=True,
+  #  bnb_4bit_quant_type="nf4",
+   # bnb_4bit_compute_dtype=torch.bfloat16
+#)
 
 tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config, device_map='auto')
+model = AutoModelForCausalLM.from_pretrained(model_id, device_map='auto')
 tokenizer.padding_side = 'right'