removed quantization because no GPU :/

app.py

@@ -17,19 +17,19 @@ SYSTEM_PROMPT = """Answer the following question truthfully.
 USER_PROMPT = lambda x: f"""<HUMAN>: {x}\n<ASSISTANT>: """
 ADD_RESPONSE = lambda x, y: f"""<HUMAN>: {x}\n<ASSISTANT>: {y}"""
 
-bnb_config = BitsAndBytesConfig(
-    load_in_4bit=True,
-    bnb_4bit_quant_type="nf4",
-    bnb_4bit_use_double_quant=True,
-    bnb_4bit_compute_dtype=torch.float16,
-)
+# bnb_config = BitsAndBytesConfig(
+#     load_in_4bit=True,
+#     bnb_4bit_quant_type="nf4",
+#     bnb_4bit_use_double_quant=True,
+#     bnb_4bit_compute_dtype=torch.float16,
+# )
 
 config = PeftConfig.from_pretrained(PEFT_MODEL)
 
 peft_base_model = AutoModelForCausalLM.from_pretrained(
     config.base_model_name_or_path,
     return_dict=True,
-    quantization_config=bnb_config,
+    # quantization_config=bnb_config,
     device_map="auto",
     trust_remote_code=True,
 )