Update README.md

README.md

@@ -60,11 +60,36 @@ This model is not suitable for general-purpose conversation or tasks unrelated t
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
+# Load the tokenizer and model
 tokenizer = AutoTokenizer.from_pretrained("Ellbendls/Qwen-2.5-3b-Quran")
 model = AutoModelForCausalLM.from_pretrained("Ellbendls/Qwen-2.5-3b-Quran")
 
-input_text = "Apa tafsir dari Surat Al-Fatihah ayat 1?"
-inputs = tokenizer(input_text, return_tensors="pt")
-outputs = model.generate(**inputs)
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+# Move the model to GPU
+model.to("cuda")
+
+# Define the input message
+messages = [
+    {
+        "role": "user", 
+        "content": "Tafsirkan ayat ini اِهْدِنَا الصِّرَاطَ الْمُسْتَقِيْمَۙ"
+    }
+]
+
+# Generate the prompt using the tokenizer
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, 
+                                       add_generation_prompt=True)
+
+# Tokenize the prompt and move inputs to GPU
+inputs = tokenizer(prompt, return_tensors='pt', padding=True, 
+                   truncation=True).to("cuda")
+
+# Generate the output using the model
+outputs = model.generate(**inputs, max_length=150, 
+                         num_return_sequences=1)
+
+# Decode the output
+text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+# Print the result
+print(text.split("assistant")[1])
 ```