Update README.md

README.md

@@ -36,6 +36,63 @@ This is the model card of a 🤗 transformers model that has been pushed on the
 - **Demo [optional]:** [More Information Needed]
 
 ## Uses
+```
+import os
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
+from peft import PeftModel
+
+model_id = 'model_result'
+
+bnb_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_quant_type="nf4",
+    bnb_4bit_compute_dtype=torch.bfloat16,
+    bnb_4bit_use_double_quant=True,
+)
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+tokenizer.pad_token = tokenizer.eos_token
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    #torch_dtype=torch.bfloat16,
+    quantization_config=bnb_config, # 4-bit quantization (4비트 양자화)
+    device_map="auto",
+)
+
+model.eval()
+
+from transformers import TextStreamer
+
+def inference(input: str):
+    streamer = TextStreamer(tokenizer=tokenizer, skip_prompt=True, skip_special_tokens=True)
+    
+    messages = [
+        {"role": "system", "content": "You are an information security AI assistant. Information security questions must be answered accurately."},
+        {"role": "user", "content": f"Please provide concise, non-repetitive answers to the following questions:\n {input}"}
+        # {"role": "user", "content": f"{input}"}
+        ]
+    
+    input_ids = tokenizer.apply_chat_template(
+        messages,
+        tokenize=True,
+        add_generation_prompt=True,
+        return_tensors="pt",
+    ).to(model.device)
+    
+    outputs = model.generate(
+        input_ids,
+        streamer=streamer,
+        max_new_tokens=8192,
+        num_beams=1,
+        do_sample=True,
+        temperature=0.1,
+        top_p=0.95,
+        top_k=10
+    )
+
+```
 
 <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->