Update README.md
Browse files
README.md
CHANGED
|
@@ -57,11 +57,12 @@ After intense refining, <b>Nerdsking-python-coder-3B-i</b> has achieved <b>88.41
|
|
| 57 |
</p>
|
| 58 |
<p class="justified-text">
|
| 59 |
<i> Note: Quantized variants (INT4/INT6) may exhibit lower HumanEval scores due to reduced numerical precision.</i>
|
|
|
|
| 60 |
<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
|
| 61 |
- the model reasoning was right
|
| 62 |
- the failure is syntactic / boilerplate, not conceptual
|
| 63 |
If considered those extra 5 questions as correct, our benchmark would be much higher.
|
| 64 |
-
|
| 65 |
|
| 66 |
</p>
|
| 67 |
|
|
|
|
| 57 |
</p>
|
| 58 |
<p class="justified-text">
|
| 59 |
<i> Note: Quantized variants (INT4/INT6) may exhibit lower HumanEval scores due to reduced numerical precision.</i>
|
| 60 |
+
<hr>
|
| 61 |
<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
|
| 62 |
- the model reasoning was right
|
| 63 |
- the failure is syntactic / boilerplate, not conceptual
|
| 64 |
If considered those extra 5 questions as correct, our benchmark would be much higher.
|
| 65 |
+
<hr>
|
| 66 |
|
| 67 |
</p>
|
| 68 |
|