Update app.py

app.py

@@ -24,7 +24,6 @@ model_id = "CohereForAI/c4ai-command-r-plus-4bit"
 
 
 
-tokenizer = AutoTokenizer.from_pretrained(model_id, token= token)
 
 # 
 
@@ -39,6 +38,8 @@ def respond(
     temperature,
     top_p,
 ):
+    tokenizer = AutoTokenizer.from_pretrained(model_id, token= token)
+
     model = AutoModelForCausalLM.from_pretrained(model_id, token= token, 
                                                  # torch_dtype=torch.bfloat16,    
                                              # attn_implementation="flash_attention_2",