Update app.py

app.py

@@ -13,12 +13,7 @@ client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 token=os.getenv('token')
 print('token = ',token)
 
-from transformers import AutoTokenizer, AutoModelForCausalLM
 
-model_id = "CohereForAI/c4ai-command-r-plus-4bit"
-
-tokenizer = AutoTokenizer.from_pretrained(model_id, token= token)
-model = AutoModelForCausalLM.from_pretrained(model_id, token= token)
 
 
 
@@ -31,6 +26,12 @@ def respond(
     temperature,
     top_p,
 ):
+    from transformers import AutoTokenizer, AutoModelForCausalLM
+
+    model_id = "CohereForAI/c4ai-command-r-plus-4bit"
+
+    tokenizer = AutoTokenizer.from_pretrained(model_id, token= token)
+    model = AutoModelForCausalLM.from_pretrained(model_id, token= token)
     messages = [{"role": "user", "content": "Hello, how are you?"}]
     input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
 ## <BOS_TOKEN><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Hello, how are you?<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>