Reverted to standard text completion code for Base/CPT model representation

README.md

@@ -68,19 +68,16 @@ model, tokenizer = FastLanguageModel.from_pretrained(
 )
 FastLanguageModel.for_inference(model)
 
-messages = [
-    {"role": "system", "content": "You are Chat2Find-CPT, a helpful assistant."},
-    {"role": "user", "content": "ශ්‍රී ලංකාව ගැන කෙටි විස්තරයක්:"}
-]
-prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+prompt = "ශ්‍රී ලංකාව ගැන කෙටි විස්තරයක්:"
 
 inputs = tokenizer(
     text=[prompt],
-    return_tensors = "pt"
+    return_tensors="pt"
 ).to("cuda")
 
-outputs = model.generate(**inputs, max_new_tokens = 256)
-response = tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)
+outputs = model.generate(**inputs, max_new_tokens=256)
+# Decode the generated text
+response = tokenizer.decode(outputs[0], skip_special_tokens=True)
 print(response)
 ```