Update README.md

README.md

@@ -57,7 +57,7 @@ For more details, including benchmark evaluation, hardware requirements, and inf
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model_name = "Kwaipilot/KAT-Dev-32B"
+model_name = "Kwaipilot/KAT-Dev"
 
 # load the tokenizer and the model
 tokenizer = AutoTokenizer.from_pretrained(model_name)
@@ -94,7 +94,7 @@ print("content:", content)
 ## Claude Code
  ### vllm server
 ```
-MODEL_PATH="Kwaipilot/KAT-Dev-32B"
+MODEL_PATH="Kwaipilot/KAT-Dev"
 
 vllm serve $MODEL_PATH \
       --enable-prefix-caching \