Update app.py

app.py

@@ -168,7 +168,7 @@ print("Running LLM Zephyr")
 llm_zephyr = Llama(model_path=zephyr_model_path,n_gpu_layers=GPU_LAYERS,max_new_tokens=256, context_window=4096, n_ctx=4096,n_batch=128,verbose=LLAMA_VERBOSE)
 
 print("Running Yi LLM")
-llm_yi = Llama(model_path=yi_model_path,n_gpu_layers=GPU_LAYERS,max_new_tokens=256, context_window=4096, n_ctx=4096,n_batch=128,verbose=LLAMA_VERBOSE,model_type="mistral")
+llm_yi = Llama(model_path=yi_model_path,n_gpu_layers=GPU_LAYERS,max_new_tokens=256, context_window=4096, n_ctx=4096,n_batch=128,verbose=LLAMA_VERBOSE)
 
 
 # Mistral formatter