Update README.md

README.md

@@ -8999,7 +8999,7 @@ Stage4: Alignment between *jasper token embeddings from image's detailed caption
 I use a AdaptiveAvgPool2d to do an adjustment on vision tokens' number and dimensions, this method does not need additional parameters.
 
 **The meaning of distillation is to achieve better results with smaller models or as a way of pre-training, not to hit the top of the leaderboards.**
-Actually, I've got first place on MTEB (Chinese and English), I will not release the two models, as I said before, it's meaningless. 
+Actually, I've got first place on MTEB (Chinese and English), I will not release the two models, as I said before, it's meaningless and has poor generalisability.