Update README.md
Browse files
README.md
CHANGED
|
@@ -87,7 +87,7 @@ Both GTE-ModernColBERT and ColBERT-small model cards have this comparison agains
|
|
| 87 |
-----
|
| 88 |
|
| 89 |
|
| 90 |
-
# Running inference:
|
| 91 |
|
| 92 |
There are really strong storage and retrieval abstractions: VectorDBs like Qdrant, Weaviate or Vespa that support multi-vectors and strong Colbert training libraries like PyLate, So we feel it is best to work the authors and integrate.
|
| 93 |
For now we offer only code to load the model, run inference and do some light weight in-memory ranking (no heavy lifting like storing and retrieving using FAISS indexes).
|
|
|
|
| 87 |
-----
|
| 88 |
|
| 89 |
|
| 90 |
+
# How to use / Running inference:
|
| 91 |
|
| 92 |
There are really strong storage and retrieval abstractions: VectorDBs like Qdrant, Weaviate or Vespa that support multi-vectors and strong Colbert training libraries like PyLate, So we feel it is best to work the authors and integrate.
|
| 93 |
For now we offer only code to load the model, run inference and do some light weight in-memory ranking (no heavy lifting like storing and retrieving using FAISS indexes).
|