Update README.md

README.md

@@ -3,4 +3,31 @@ library_name: peft
 base_model: bigscience/bloom-3b
 ---
 
-Low Rank Adapter for Bloom decoder for question answering
+Low Rank Adapter for Bloom decoder for question answering
+
+# Example usage:
+    import torch
+    from peft import PeftModel, PeftConfig
+    from transformers import AutoModelForCausalLM, AutoTokenizer
+    from IPython.display import display, Markdown
+
+    peft_model_id = "Jayveersinh-Raj/bloom-que-ans"
+    config = PeftConfig.from_pretrained(peft_model_id)
+    model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path, return_dict=True, load_in_8bit=False, device_map='auto')
+    tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
+
+    # Load the Lora model
+    qa_model = PeftModel.from_pretrained(model, peft_model_id)
+
+    def make_inference(context, question):
+      batch = tokenizer(f"### CONTEXT\n{context}\n\n### QUESTION\n{question}\n\n### ANSWER\n", return_tensors='pt').to("cuda")
+
+     with torch.cuda.amp.autocast():
+       output_tokens = qa_model.generate(**batch, max_new_tokens=200)
+
+     display(Markdown((tokenizer.decode(output_tokens[0], skip_special_tokens=True))))
+
+context = ""
+question = "What is the best food?"
+
+make_inference(context, question)