Upload /README.md with huggingface_hub

README.md

@@ -74,7 +74,7 @@ tok = AutoTokenizer.from_pretrained(BASE_MODEL, use_fast=False)
 streamer = TextStreamer(tok)
 ```
 
-I have done some test in this notebook
+I have done some tests in this notebook
 https://colab.research.google.com/gist/sharpbai/745fa7c6b2069544c254b1fb73070698/infer-with-onnxruntime-vs-transformers-llama-13b.ipynb
 
 ## Original model card