Add usage

README.md

@@ -94,6 +94,20 @@ python3 zipnn_decompress_path.py --path .
 ```
 
 Now just run the local version of the model.
+# Use a pipeline as a high-level helper
+from transformers import pipeline
+
+messages = [
+    {"role": "user", "content": "Who are you?"},
+]
+pipe = pipeline("text-generation", model="PATH_TO_MODEL") # "." if in directory
+pipe(messages)
+
+# Load model directly
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("PATH_TO_MODEL") # "." if in directory
+model = AutoModelForCausalLM.from_pretrained("PATH_TO_MODEL") # "." if in directory
 
 ## Prompt Template