Update app.py

app.py

@@ -18,7 +18,10 @@ nf4_config = BitsAndBytesConfig(
 
 model_id = "CohereForAI/c4ai-command-r-v01"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id,quantization_config=nf4_config)
+model = AutoModelForCausalLM.from_pretrained(model_id,
+                                             load_in_8bit=True,
+                                             # quantization_config=nf4_config
+                                            )
 
 @spaces.GPU
 def generate_response(user_input, max_new_tokens, temperature):