Update README.md

README.md

@@ -62,15 +62,15 @@ KeyError: 'qwen2'
 Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents.
 
 ```python
-from modelscope import AutoModelForCausalLM, AutoTokenizer
+from transformers import AutoModelForCausalLM, AutoTokenizer
 device = "cuda" # the device to load the model onto
 
 model = AutoModelForCausalLM.from_pretrained(
-    "huangjintao/Qwen1.5-110B-Chat-GPTQ-Int8",
+    "study-hjt/Qwen1.5-110B-Chat-GPTQ-Int8",
     torch_dtype="auto",
     device_map="auto"
 )
-tokenizer = AutoTokenizer.from_pretrained("huangjintao/Qwen1.5-110B-Chat-GPTQ-Int8")
+tokenizer = AutoTokenizer.from_pretrained("study-hjt/Qwen1.5-110B-Chat-GPTQ-Int8")
 
 prompt = "Give me a short introduction to large language model."
 messages = [