Update README.md

README.md

@@ -63,6 +63,9 @@ model = AutoModelForCausalLM.from_pretrained(
 # Step 3: Load the tokenizer
 tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True, token = HF_TOKEN)
 
+# Integrate the LoRA adapter into the base model.  
+model = PeftModel.from_pretrained(model, adapter_id, token=HF_TOKEN)
+
 # Step 4: Load dataset
 datasets = []
 with open("./elyza-tasks-100-TV_0.jsonl", "r") as f:
@@ -74,6 +77,11 @@ with open("./elyza-tasks-100-TV_0.jsonl", "r") as f:
         datasets.append(json.loads(item))
         item = ""
 
+# Perform inference using the model.
+
+# Switch the model to inference mode
+FastLanguageModel.for_inference(model)
+
 # Step 5: Run inference on dataset
         results = []
 for data in tqdm(datasets):