Update README.md

README.md

@@ -1,5 +1,46 @@
 ---
 license: bigscience-openrail-m
 base_model:
-- Qwen/Qwen2.5-3B-Instruct
----
+  - meta-llama/Llama-3.2-3B
+  - Qwen/Qwen2.5-3B-Instruct
+---
+
+
+The following example illustrates how to load the FineEdit-XL adapter for inference.
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+import torch
+
+## Base Model
+base_model = "meta-llama/Llama-3.2-3B"
+
+## Lora
+adapter_model = "YimingZeng/FineEdit_Model"
+
+subfolder = "FineEdit-XL"
+
+## Load tokenizer and base model
+tokenizer = AutoTokenizer.from_pretrained(base_model)
+base = AutoModelForCausalLM.from_pretrained(
+    base_model,
+    torch_dtype=torch.bfloat16,
+    device_map="auto"
+)
+
+## Load LoRA adapter
+model = PeftModel.from_pretrained(base, adapter_model, subfolder=subfolder)
+
+## Test
+prompt = """Edit Request: Please change 'Captain American' to 'Iron Man'.
+Original Content: 'Captain American' is a superhero.
+Edited Content:
+"""
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+
+with torch.no_grad():
+    outputs = model.generate(**inputs, max_new_tokens=100)
+
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```