Update README.md

README.md

@@ -42,7 +42,30 @@ Fine-tuning was done using ORPO. The dataset was generated using GPT-4o (selecte
 
 ### Direct Use
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+```python
+import transformers
+import torch
+
+model_id = "Kkaastr/Devple-8B"
+
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model_id,
+    model_kwargs={"torch_dtype": torch.bfloat16},
+    device_map="auto",
+)
+
+messages = [
+    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
+    {"role": "user", "content": "Who are you?"},
+]
+
+outputs = pipeline(
+    messages,
+    max_new_tokens=256,
+)
+print(outputs[0]["generated_text"][-1])
+```
 
 [More Information Needed]