update

models/cpp_qwen2.py

@@ -27,7 +27,7 @@ class Qwen2Simulator(Simulator):
             # n_gpu_layers=-1, # Uncomment to use GPU acceleration
             # seed=1337, # Uncomment to set a specific seed
             # n_ctx=2048, # Uncomment to increase the context window
-            tokenizer=self.hf_tokenizer,
+            tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer(self.hf_tokenizer),
             verbose=False,
         )