Update README.md

README.md

@@ -18,7 +18,7 @@ Impact of quantization on a set of models.
 Evaluation of the model was conducted using the PoLL (Pool of LLM) technique, assessing performance on **100 French questions** with scores aggregated from six evaluations
 (two per evaluator). The evaluators included GPT-4o, Gemini-1.5-pro, and Claude3.5-sonnet.
 
-**Performance Scores (on a scale of 5):**
+Performance Scores (on a scale of 5):
 | Model                                        | Score   | # params |
 |---------------------------------------------:|:-------:|:--------:|
 | gpt-4o                                       | 4.13    | N/A      |