Update README.md

README.md

@@ -139,9 +139,7 @@ The model was trained in two stages. In the first stage, MLP layers were trained
 
 | Model                                      | Score  | 95% CI | Avg. #Tokens |
 |---------------------------------------------|-------|-------------------------|---------------|
-| **Cotype-Nano**                           | **31.2**  | **+1.7 / -1.9**            | **567**           |
-| hermes-2-pro-llama-3-8b                     | 30.8  | +2.0 / 2.2              | 463.45        |
-| openchat-3.6-8b-20240522                    | 30.3  | +2.2 / -1.6              | 428.7         |
+| **Cotype-Nano**                           | **30.2**  | **+2.2 / -1.3**            | **567**           |
 | vikhr-it-5.3-fp16-32k                       | 27.8  | +1.5 / -2.1              | 519.71        |
 | vikhr-it-5.3-fp16                           | 22.73 | +1.8 / -1.7             | 523.45        |
 | kolibri-vikhr-mistral-0427                  | 22.41 | +1.6 / -1.9             | 489.89        |