Update README.md

README.md

@@ -130,18 +130,15 @@ This is a simple example of how to use **PowerMoE-3b** model.
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 device = "cuda" # or "cpu"
-model_path = "ibm/PowerMoE-3b"
+model_path = "ibm/PowerLM-3b"
 tokenizer = AutoTokenizer.from_pretrained(model_path)
 # drop device_map if running on CPU
 model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device)
 model.eval()
 # change input text as desired
-chat = [
-    { "role": "user", "content": "Write a code to find the maximum value in a list of numbers." },
-]
-chat = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
+prompt = "Write a code to find the maximum value in a list of numbers."
 # tokenize the text
-input_tokens = tokenizer(chat, return_tensors="pt")
+input_tokens = tokenizer(prompt, return_tensors="pt")
 # transfer tokenized inputs to the device
 for i in input_tokens:
     input_tokens[i] = input_tokens[i].to(device)