Update README.md

README.md

@@ -4,4 +4,16 @@ base_model:
 - intfloat/multilingual-e5-small
 ---
 
-rename Data to Model.mlpackage
+the original model is OriginalModel.mlpackage with float32
+
+# the quantization model info :
+
+## quantization and input maxlength
+
+coreML: using linear quantize nbit=8
+
+input max = 128
+
+## note
+
+i tried turn it into float`6, but it changed too much for its prediction. quantization using linear nbit=8, it works almost like the original.