appvoid commited on
Commit
1e25778
·
verified ·
1 Parent(s): da2d372

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -0
README.md CHANGED
@@ -8,6 +8,14 @@ This is a repo created to keep a collection of quantized bert models in ggml for
8
  ### usage
9
  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 test `large` model for real use-case scenarios.
10
 
 
 
 
 
 
 
 
 
11
  ### embeddings sample
12
 
13
  ```
 
8
  ### usage
9
  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 test `large` model for real use-case scenarios.
10
 
11
+ | model | size (mb) |
12
+ | ---- | ---- |
13
+ | small | 11.2 |
14
+ | medium | 14.5 |
15
+ | large (api) | 21.3 |
16
+
17
+ We are planning to expand the list to support as many open-source models as possible.
18
+
19
  ### embeddings sample
20
 
21
  ```