Update README.md
Browse files
README.md
CHANGED
@@ -1,14 +1,14 @@
|
|
1 |
-
---
|
2 |
-
library_name: sentence-transformers
|
3 |
-
pipeline_tag: sentence-similarity
|
4 |
-
tags:
|
5 |
-
- sentence-transformers
|
6 |
-
- sentence-similarity
|
7 |
-
license: mit
|
8 |
-
language:
|
9 |
-
- en
|
10 |
-
- ru
|
11 |
-
---
|
12 |
|
13 |
# Multilingual E5 WB
|
14 |
|
@@ -17,8 +17,8 @@ Fine-tuned version of default [multilingual-e5-base](https://huggingface.co/intf
|
|
17 |
## Evaluation Results
|
18 |
|
19 |
<!--- Describe how your model was evaluated -->
|
20 |
-
As model is used as retriever, goal was to boost its performance at cosine similarity between question and answer
|
21 |
-
With given dataset of QA pairs model performance on EmbeddingSimilarityEvaluator improved from 0.62 to 0.78
|
22 |
|
23 |
|
24 |
## Fine Tuning
|
|
|
1 |
+
---
|
2 |
+
library_name: sentence-transformers
|
3 |
+
pipeline_tag: sentence-similarity
|
4 |
+
tags:
|
5 |
+
- sentence-transformers
|
6 |
+
- sentence-similarity
|
7 |
+
license: mit
|
8 |
+
language:
|
9 |
+
- en
|
10 |
+
- ru
|
11 |
+
---
|
12 |
|
13 |
# Multilingual E5 WB
|
14 |
|
|
|
17 |
## Evaluation Results
|
18 |
|
19 |
<!--- Describe how your model was evaluated -->
|
20 |
+
As model is used as retriever, **goal was to boost its performance at cosine similarity between question and answer.**
|
21 |
+
With given dataset of QA pairs model performance on EmbeddingSimilarityEvaluator improved from **0.62 to 0.78.**
|
22 |
|
23 |
|
24 |
## Fine Tuning
|