Update README.md

README.md

@@ -66,4 +66,25 @@ Who are you?<|im_end|>
 
 Monad has no support yet for multi-turn.
 
-A major envisioned use case for Monad is explainability, as the model does provide a unique trade-off between observability and actual reasoning performance.
+A major envisioned use case for Monad is explainability, as the model does provide a unique trade-off between observability and actual reasoning performance.
+
+Use with Transformers (Directly)
+```zsh
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+prompt = "Hi i am Kabil?\nAssistant:"
+
+input_token = tokenizer(
+    prompt,
+    return_tensors = "pt"
+  )
+input_token.pop("token_type_ids", None)
+input_token = input_token.to(model.device)
+
+outputs = model.generate(
+    **input_token,
+    max_new_tokens=40
+  )
+
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```