Update README.md
Browse files
README.md
CHANGED
|
@@ -11,7 +11,7 @@ language:
|
|
| 11 |
|
| 12 |
This is a smaller version of the **intfloat/multilingual-e5-base** with only some Russian (Cyrillic in general) and English (fever) tokens (and embeddings) left.
|
| 13 |
|
| 14 |
-
The model created in a similar way as described in this https://
|
| 15 |
|
| 16 |
The **CulturaX** dataset was used to search for the required tokens. As a result, out of 250k tokens of the original model, only **69,382** required were left.
|
| 17 |
|
|
|
|
| 11 |
|
| 12 |
This is a smaller version of the **intfloat/multilingual-e5-base** with only some Russian (Cyrillic in general) and English (fever) tokens (and embeddings) left.
|
| 13 |
|
| 14 |
+
The model created in a similar way as described in this https://medium.com/m/global-identity-2?redirectUrl=https%3A%2F%2Ftowardsdatascience.com%2Fhow-to-adapt-a-multilingual-t5-model-for-a-single-language-b9f94f3d9c90 post.
|
| 15 |
|
| 16 |
The **CulturaX** dataset was used to search for the required tokens. As a result, out of 250k tokens of the original model, only **69,382** required were left.
|
| 17 |
|