prithivida
commited on
Commit
•
14b96ee
1
Parent(s):
4ecfcd3
Update README.md
Browse files
README.md
CHANGED
@@ -145,7 +145,7 @@ for query, query_embedding in zip(queries, query_embeddings):
|
|
145 |
# FAQs:
|
146 |
|
147 |
#### How can I reduce overall inference cost ?
|
148 |
-
- You host these models without heavy torch dependency using the ONNX flavours of these models via [FlashRetrieve](https://github.com/PrithivirajDamodaran/FlashRetrieve) library.
|
149 |
|
150 |
|
151 |
#### How do I reduce vector storage cost ?
|
|
|
145 |
# FAQs:
|
146 |
|
147 |
#### How can I reduce overall inference cost ?
|
148 |
+
- You can host these models without heavy torch dependency using the ONNX flavours of these models via [FlashRetrieve](https://github.com/PrithivirajDamodaran/FlashRetrieve) library.
|
149 |
|
150 |
|
151 |
#### How do I reduce vector storage cost ?
|