update

app.py

@@ -51,14 +51,6 @@ h1 {
 # Load the tokenizer and model
 tokenizer = AutoTokenizer.from_pretrained("FreedomIntelligence/Apollo-7B")
 
-chat = [
-  {"role": "user", "content": "Hello, how are you?"},
-  {"role": "assistant", "content": "I'm doing great. How can I help you today?"},
-  {"role": "user", "content": "I'd like to show off how chat templating works!"},
-]
-
-tokenizer.apply_chat_template(chat, tokenize=False)
-
 model = AutoModelForCausalLM.from_pretrained("FreedomIntelligence/Apollo-7B", device_map="auto")  # to("cuda:0") 
 terminators = [
     tokenizer.eos_token_id,