Nerdsking
/

nerdsking-python-coder-3B-i

Text Generation

Model card Files Files and versions

Nerdsking commited on 15 days ago

Commit

7a3578f

·

verified ·

1 Parent(s): 35dbdab

Update README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -56,15 +56,15 @@ After intense refining, <b>Nerdsking-python-coder-3B-i</b> has achieved <b>88.41
 <i>The configuration above is fully disclosed to support reproducibility and fair comparison.</i>
 </p>
 <p class="justified-text">
-<i> Note: Quantized variants (INT4/INT6) may exhibit lower HumanEval scores due to reduced numerical precision.</i>
   <hr>
 <br><b>IMPORTANT:</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.
 <hr>
-</p>
 #### Comparison Table

 <i>The configuration above is fully disclosed to support reproducibility and fair comparison.</i>
 </p>
 <p class="justified-text">
+<i> Note: Quantized variants (INT4/INT6) may exhibit lower HumanEval scores due to reduced numerical precision.</i></p>
   <hr>
 <br><b>IMPORTANT:</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<br>
 If considered those extra 5 questions as correct, our benchmark would be much higher.
 <hr>
 #### Comparison Table