use repo model

README.md

@@ -65,7 +65,7 @@ You can use transformers to run inference with Yi-Coder models (both chat and ba
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
 device = "cuda" # the device to load the model onto
-model_path = "01-ai/Yi-Coder-9B-Chat"
+model_path = "01-ai/Yi-Coder-1.5B-Chat"
 
 tokenizer = AutoTokenizer.from_pretrained(model_path)
 model = AutoModelForCausalLM.from_pretrained(model_path, device_map="auto").eval()