Update README.md

README.md

@@ -19,8 +19,6 @@ tags:
 #### Model Details
 
 
-(<b><font color=red>Much better than Nanbeige/Nanbeige4.1-3B</font>. Verify why!</b>)
-
 
 <p class="justified-text">
 <b>Nerdsking-python-coder-3B-i</b> is a 3B parameter <u>partially uncensored</u> model focused in <b> Python</b>, with <b>English</b> as main language. It was massively trained in python, therefore despite the fact it can code in other languages as well, the performance will be not in the same level as the one achieved while using python.
@@ -126,9 +124,7 @@ We did not considered it for our score, but "if" considered those extra 5 questi
 ### <font color=red>Nerdsking/nerdsking-python-coder-3B-i</font> (real 3 billion model) with 88,41% HumanEval accuracy in Python (FP16)
 - Time to finish 160 questions from HumanEval: 210.51s --- <b><u>THREE MINUTES AND HALF</b></u> !!! (in a RTX 5060 ti 16gb)
 
-<b><i><font color=red>Lesson: Anyone can create a bigger model with an "eternal loop" to solve problems by randomly trying all possible variables. That is not "intelligence", that's 
-mere BRUTE FORCE, and waste of time and resources. INTELLIGENCE is doing MORE, with LESS and EFFICIENCY. </b></font></i>
- 
+
 <hr>