Update README.md

README.md

@@ -86,13 +86,11 @@ model = PeftModel.from_pretrained(model, "TuningAI/Llama2_13B_startup_Assistant"
 tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-13b-hf", trust_remote_code=True)
 tokenizer.pad_token = tokenizer.eos_token
 tokenizer.padding_side = "right"
+system_message = "Given a user's startup-related question in English, you will generate a thoughtful answer in English."
 while 1:
   input_text = input(">>>")
   prompt = f"[INST] <<SYS>>\n{system_message}\n<</SYS>>\n\n {input_text}. [/INST]"
-  num_new_tokens = 512
-  num_prompt_tokens = len(tokenizer(prompt)['input_ids'])
-  max_length = num_prompt_tokens + num_new_tokens
-  pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=max_length)
+  pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=400)
   result = pipe(prompt)
   print(result[0]['generated_text'].replace(prompt, ''))
 ```