Update README.md

README.md

@@ -55,6 +55,13 @@ ltc_layers = 2
 pip install transformers torch numpy
 ```
 
+## Inference
+This gist has full code for inference
+
+``` bash
+https://gist.github.com/harishsg993010/e632de8b15a3ab1ff03e3912f55109ea
+```
+
 ## Evaluation
 
 I performed evaluation using the standard lm-evaluation-harness setup. Following similar methodology to TinyLlama and MicroLlama, I used acc_norm for most datasets except for winogrande and boolq which used acc as the metrics.