Update README.md

README.md

@@ -57,6 +57,12 @@ After intense refining, <b>Nerdsking-python-coder-3B-i</b> has achieved <b>88.41
 </p>
 <p class="justified-text">
 <i> Note: Quantized variants (INT4/INT6) may exhibit lower HumanEval scores due to reduced numerical precision.</i>
+<b>IMPORTANT:</b>b About 5 "errors" from the model during the benchmark were mere "import errors" (missing imports (reduce, Optional, List, etc ), but the logic was perfect, therefore
+- the model reasoning was right
+- the failure is syntactic / boilerplate, not conceptual
+If considered those extra 5 questions as correct, our benchmark would be much higher.
+
+  
 </p>