Update README.md

README.md

@@ -48,6 +48,8 @@ FastApply-1.5B-v1.0 is intended for use in AI-powered code editors and tools tha
 FastApply-1.5B-v1.0 is based on the Qwen2.5 Coder architecture and is fine-tuned for code editing tasks. It uses a specific prompt structure for inference:
 
 ```
+<|im_start|>system
+You are a coding assistant that helps merge code updates, ensuring every modification is fully integrated.<|im_end|>
 <|im_start|>user
 Merge all changes from the <update> snippet into the <code> below.
 - Preserve the code's structure, order, comments, and indentation exactly.
@@ -58,13 +60,13 @@ Merge all changes from the <update> snippet into the <code> below.
 
 <update>{update_snippet}</update>
 
-Provide the complete updated code."""
+Provide the complete updated code.<|im_end|>
+<|im_start|>assistant
 ```
 
 The model's output is structured as:
 
 ```
-<|im_start|>assistant
 <updated-code>[Full-complete updated file]</updated-code>
 ```
 
@@ -83,7 +85,9 @@ model = AutoModelForCausalLM.from_pretrained("Kortix/FastApply-1.5B-v1.0")
 tokenizer = AutoTokenizer.from_pretrained("Kortix/FastApply-1.5B-v1.0")
 
 # Prepare your input following the prompt structure mentioned above
-input_text = """<|im_start|>user
+input_text = """<|im_start|>system
+You are a coding assistant that helps merge code updates, ensuring every modification is fully integrated.<|im_end|>
+<|im_start|>user
 Merge all changes from the <update> snippet into the <code> below.
 - Preserve the code's structure, order, comments, and indentation exactly.
 - Output only the updated code, enclosed within <updated-code> and </updated-code> tags.
@@ -93,7 +97,9 @@ Merge all changes from the <update> snippet into the <code> below.
 
 <update>{update_snippet}</update>
 
-Provide the complete updated code."""
+Provide the complete updated code.<|im_end|>
+<|im_start|>assistant
+"""
 
 input_text = input_text.format(
     original_code=original_code,