Update app.py

app.py

@@ -10,13 +10,13 @@ hf_token = os.environ.get("HF_TOKEN")
 model_id = "mistralai/Mistral-7B-Instruct-v0.2"
 
 
-quantization_config = BitsAndBytesConfig(
-    load_in_4bit=True,
-    bnb_4bit_quant_type="nf4",
-    bnb_4bit_compute_dtype=torch.float16
-)
+# quantization_config = BitsAndBytesConfig(
+#     load_in_4bit=True,
+#     bnb_4bit_quant_type="nf4",
+#     bnb_4bit_compute_dtype=torch.float16
+# )
 
-model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=True, device_map="auto", token=hf_token)
+model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", token=hf_token)
 tokenizer = AutoTokenizer.from_pretrained(model_id, token=hf_token)
 
 def format_prompt(message, history):