Update README.md

README.md

@@ -9,6 +9,18 @@ This is a repo created to keep a collection of quantized bert models in ggml for
 You can utilize [bert.cpp](https://github.com/skeskinen/bert.cpp) as usual or use [our new api](https://rapidapi.com/nohakcoffee/api/simple-similarity) to quickly prototype on real use-case scenarios for text similarity.
 
 
+### embeddings sample
+
+```
+./main -m small -p "word"
+// [0.0698, -0.0024, -0.0153, 0.0193, -0.1060, -0.0278, 0.1424, -0.0056, -0.0536...
+```
+
+### api reference
+
+We are planning to update the list to always support lastest open-source models.
+
+
 | api | size |
 | ---- | ---- |
 | nano | 11.2 |
@@ -17,19 +29,7 @@ You can utilize [bert.cpp](https://github.com/skeskinen/bert.cpp) as usual or us
 | large | 68.8 |
 
 
-We are planning to update the list to always support lastest open-source models.
-
-### embeddings sample
-
-```
-./main -m small -p "word"
-[0.0698, -0.0024, -0.0153, 0.0193, -0.1060, -0.0278, 0.1424, -0.0056, -0.0536...
 ```
-
-### api sample
-
-```
-
 { ...,
   "similarity": {
     "semantic": 0.035270897102758283,