Update README.md

README.md

@@ -11,6 +11,25 @@ tags: []
 
 ## Model Details
 
+### Code to generate model
+
+```py
+from transformers import GraniteConfig, GraniteForCausalLM, AutoTokenizer
+
+model = GraniteForCausalLM(GraniteConfig(
+    hidden_size=32,
+    intermediate_size=64,
+    num_attention_heads=4,
+    num_hidden_layers=2,
+    num_key_value_heads=4,
+    pad_token_id=0,
+))
+tokenizer = AutoTokenizer.from_pretrained('ibm/PowerLM-3b')
+
+model.push_to_hub('hf-internal-testing/tiny-random-GraniteForCausalLM')
+tokenizer.push_to_hub('hf-internal-testing/tiny-random-GraniteForCausalLM')
+```
+
 ### Model Description
 
 <!-- Provide a longer summary of what this model is. -->