Update README.md

README.md

@@ -15,13 +15,13 @@ Our Model is fine tuned on Llama-2 7B model on text-2-sql Dataset on alpaca form
 
 # Inference
 ```python
-!pip install transformers accelerate xformers
+!pip install transformers accelerate xformers bitsandbytes
 
-# Load model directly
 from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 
 tokenizer = AutoTokenizer.from_pretrained("ekshat/Llama-2-7b-chat-finetune-for-text2sql")
-model = AutoModelForCausalLM.from_pretrained("ekshat/Llama-2-7b-chat-finetune-for-text2sql")
+# Load model directly
+model = AutoModelForCausalLM.from_pretrained("ekshat/Llama-2-7b-chat-finetune-for-text2sql", load_in_4bit=True)
 
 context = "CREATE TABLE head (name VARCHAR, born_state VARCHAR, age VARCHAR)"
 question = "List the name, born state and age of the heads of departments ordered by age."
@@ -32,7 +32,8 @@ prompt = f"""Below is an context that describes a sql query, paired with an ques
 ### Question:
 {question}
 ### Answer:"""
+
 pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=200)
 result = pipe(prompt)
-  print(result[0]['generated_text'])
+print(result[0]['generated_text'])
 ```