Update README.md

README.md

@@ -32,8 +32,9 @@ Model then converted Q5_K_M gguf using llama.cpp https://github.com/ggerganov/ll
 
 2. ## Run the model
 
-```
+```python
 from transformers import AutoTokenizer
+from llama_cpp import Llama
 tokenizer = AutoTokenizer.from_pretrained('google/gemma-7b')
 example = [{'content': 'You are a financial expert and you can answer any questions related to finance. You will be given a context and a question. Understand the given context and\n        try to answer. Users will ask you questions in English and you will generate answer based on the provided CONTEXT.\n        CONTEXT:\n        D. in Forced Migration from the University of the Witwatersrand (Wits) in Johannesburg, South Africa; A postgraduate diploma in Folklore & Cultural Studies at Indira Gandhi National Open University (IGNOU) in New Delhi, India; A Masters of International Affairs at Columbia University; A BA from Barnard College at Columbia University\n', 'role': 'system'}, {'content': ' In which universities did the individual obtain their academic qualifications?\n', 'role': 'user'}, {'content': ' University of the Witwatersrand (Wits) in Johannesburg, South Africa; Indira Gandhi National Open University (IGNOU) in New Delhi, India; Columbia University; Barnard College at Columbia University.', 'role': 'assistant'}]
 prompt = tokenizer.apply_chat_template(example[:2], tokenize=False, add_generation_prompt=True)