Update README.md

README.md

@@ -43,7 +43,24 @@ The model is not guaranteed to perform well for languages other than the 10 lang
 
 ## Bias, Risks, and Limitations
 
-TowerBase-v0.1 has not been aligned to human preferences, so the model may generate problematic outputs (e.g., hallucinations, harmful content, or false statements).  
+TowerBase-v0.1 has not been aligned to human preferences, so the model may generate problematic outputs (e.g., hallucinations, harmful content, or false statements). 
+
+## Run the model
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "Unbabel/TowerBase-7B-v0.1"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+model = AutoModelForCausalLM.from_pretrained(model_id)
+
+text = "English: My name is TowerBase.\nPortuguese:"
+inputs = tokenizer(text, return_tensors="pt")
+
+outputs = model.generate(**inputs, max_new_tokens=20)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
 
 ### Training Data