Update README.md

README.md

@@ -27,6 +27,34 @@ The model was trained on a custom dataset containing clinical surgery Q&A pairs.
 Open-source medical books
 Medical catalogs
 
+Ruuning the model through Adapter Merge: 
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+import torch
+
+base_model_name = "unsloth/Llama-3.2-3B-Instruct"  
+base_model = AutoModelForCausalLM.from_pretrained(base_model_name, torch_dtype=torch.float16, device_map="auto")
+
+adapter_path = "vishal042002/Llama3.2-3b-Instruct-ClinicalSurgery"
+base_model = PeftModel.from_pretrained(base_model, adapter_path)
+
+tokenizer = AutoTokenizer.from_pretrained(base_model_name)
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+base_model.to(device)
+
+# Sample usage
+input_text = "What is the mortality rate for patients requiring surgical intervention who were unstable preoperatively?"
+inputs = tokenizer(input_text, return_tensors="pt").to(device)
+
+outputs = base_model.generate(**inputs, max_new_tokens=200, temperature=1.5, top_p=0.9)
+decoded_output = tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+print(decoded_output)
+```
+
 This model is designed to:
 
 Answer questions about clinical surgery procedures.