Update README.md

README.md

@@ -28,7 +28,7 @@ See the [usage instructions](#usage-example) for how to inference this model wit
 
 ## Performance Comparison
 
-#### Latency for 30 steps base and 9 steps refiner
+#### Latency for token generation
 
 Below is average latency of generating a token using a prompt of varying size using NVIDIA A100-SXM4-80GB GPU:
 
@@ -67,13 +67,13 @@ from transformers import AutoConfig, AutoTokenizer
 sess = InferenceSession("Mistral-7B-v0.1.onnx", providers = ["CUDAExecutionProvider"])
 config = AutoConfig.from_pretrained("mistralai/Mistral-7B-v0.1")
 
-new_model = ORTModelForCausalLM(sess, config, use_cache = True, use_io_binding = True)
+model = ORTModelForCausalLM(sess, config, use_cache = True, use_io_binding = True)
 
 tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-v0.1")
 
 inputs = tokenizer("Instruct: What is a fermi paradox?\nOutput:", return_tensors="pt")
 
-outputs = new_model.generate(**inputs)
+outputs = model.generate(**inputs)
 
 print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```