Commit
•
3cd52bd
1
Parent(s):
3d24c6f
Update README.md
Browse files
README.md
CHANGED
|
@@ -5,11 +5,17 @@ tags:
|
|
| 5 |
- feature-extraction
|
| 6 |
- sentence-similarity
|
| 7 |
- transformers
|
| 8 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
---
|
| 10 |
|
| 11 |
# MPNet NLI
|
| 12 |
|
|
|
|
|
|
|
| 13 |
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search. It has been fine-tuned using the **S**tanford **N**atural **L**anguage **I**nference (SNLI) dataset and returns MRR@10 and MAP scores of ~0.95 on the SNLI test set.
|
| 14 |
|
| 15 |
Find more info from [James Briggs on YouTube](https://youtube.com/c/jamesbriggs) or in the [**free** NLP for Semantic Search ebook](https://pinecone.io/learn/nlp).
|
|
|
|
| 5 |
- feature-extraction
|
| 6 |
- sentence-similarity
|
| 7 |
- transformers
|
| 8 |
+
language:
|
| 9 |
+
- en
|
| 10 |
+
license: mit
|
| 11 |
+
datasets:
|
| 12 |
+
- snli
|
| 13 |
---
|
| 14 |
|
| 15 |
# MPNet NLI
|
| 16 |
|
| 17 |
+
***Note**: The same model trained with negatives yields better performance. [Find it here](https://huggingface.co/jamescalam/mpnet-snli-negatives).*
|
| 18 |
+
|
| 19 |
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search. It has been fine-tuned using the **S**tanford **N**atural **L**anguage **I**nference (SNLI) dataset and returns MRR@10 and MAP scores of ~0.95 on the SNLI test set.
|
| 20 |
|
| 21 |
Find more info from [James Briggs on YouTube](https://youtube.com/c/jamesbriggs) or in the [**free** NLP for Semantic Search ebook](https://pinecone.io/learn/nlp).
|