Update README.md

README.md

@@ -6,4 +6,8 @@ language:
 - en
 ---
 
-This is a Llama 2 architecture model series trained on the TinyStories dataset, intended for use in the [llama2.c](https://github.com/karpathy/llama2.c) project by Andrej Karpathy
+This is a Llama 2 architecture model series trained on the TinyStories dataset, intended for use in the [llama2.c](https://github.com/karpathy/llama2.c) project by Andrej Karpathy. 
+
+trained on a single V100 32GB gpu for 3 epochs, we achieve an inference speed of ~72 tokens/sec.
+
+learn more on how to run inference in pure C using [llama2.c](https://github.com/karpathy/llama2.c)