Update README.md

README.md

@@ -74,20 +74,31 @@ Ensure you have a GPU with sufficient VRAM for 4-bit inference.
 ## Example Usage
 
 Generate text using the adapter:
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from peft import PeftModel
+import torch
 
-'prompt = "Soru: Yapay zeka nedir?\nCevap:"'
-'inputs = tokenizer(prompt, return_tensors="pt")'
+# Base model
+base_model = AutoModelForCausalLM.from_pretrained(
+    "unsloth/llama-3.1-8b-bnb-4bit",
+    device_map="auto"
+)
 
-'with torch.no_grad():'
-'    outputs = model.generate('
-'        **inputs,'
-'        max_new_tokens=50,'
-'        do_sample=True,'
-'        temperature=0.7'
-'    )'
+# LoRA adapter
+model = PeftModel.from_pretrained(base_model, "sixfingerdev/SixFinger-8B")
 
-'print(tokenizer.decode(outputs[0], skip_special_tokens=True))'
+# Tokenizer
+tokenizer = AutoTokenizer.from_pretrained("unsloth/llama-3.1-8b-bnb-4bit")
 
+# Örnek text generation
+prompt = "Soru: Yapay zeka nedir?\nCevap:"
+inputs = tokenizer(prompt, return_tensors="pt")
+with torch.no_grad():
+    outputs = model.generate(**inputs, max_new_tokens=50, do_sample=True, temperature=0.7)
+
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
 ---
 
 ## Notes