Update README.md

README.md

@@ -19,12 +19,61 @@ It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start
 
 ```python
-from transformers import pipeline
+import torch
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+from peft import PeftModel, PeftConfig
+
+# -----------------------------
+# 1. Define PEFT model ID & Checkpoint (Epoch)
+# -----------------------------
+peft_model_id = "xxccho/margin_reg_baseline_code"
+
+# [ Checkpoints to Epochs Mapping ]
+# Epoch 1  : "checkpoint-246"
+# Epoch 2  : "checkpoint-492"
+# Epoch 3  : "checkpoint-738"
+# Epoch 4  : "checkpoint-984"
+# Epoch 5  : "checkpoint-1230"
+# Epoch 6  : "checkpoint-1476"
+# Epoch 7  : "checkpoint-1722"
+# Epoch 8  : "checkpoint-1968"
+# Epoch 9  : "checkpoint-2214"
+# Epoch 10 : "checkpoint-2460"
+
+# 예시: 5 Epoch 체크포인트를 사용하려면 "checkpoint-1230" 할당. None일 시 최종(10x) 모델 로드
+checkpoint = None  
+
+# 2. Load the PEFT config
+config = PeftConfig.from_pretrained(peft_model_id, subfolder=checkpoint) if checkpoint else PeftConfig.from_pretrained(peft_model_id)
+
+# 3. Load tokenizer
+tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
+if tokenizer.pad_token is None:
+    tokenizer.pad_token = tokenizer.eos_token
+
+# 4. Load base model
+base_model = AutoModelForSequenceClassification.from_pretrained(
+    config.base_model_name_or_path,
+    num_labels=1,
+    torch_dtype=torch.bfloat16,
+    device_map="auto"
+)
+
+# 5. Apply LoRA adapter
+model = PeftModel.from_pretrained(base_model, peft_model_id, subfolder=checkpoint) if checkpoint else PeftModel.from_pretrained(base_model, peft_model_id)
+model.config.pad_token_id = tokenizer.pad_token_id
+model.eval()
+
+# Example Usage
+text = "User: Write a python code for calculating fibonacci sequence.\nAssistant: Here is the code..."
+inputs = tokenizer(text, return_tensors="pt").to(model.device)
+
+with torch.no_grad():
+    outputs = model(**inputs)
+    reward_score = outputs.logits.squeeze().item()
+
+print(f"[Code] Reward Score: {reward_score:.4f}")
 
-text = "The capital of France is Paris."
-rewarder = pipeline(model="None", device="cuda")
-output = rewarder(text)[0]
-print(output["score"])
 ```
 
 ## Training procedure