First Commit
Browse files
README.md
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
pipeline_tag: sentence-similarity
|
| 3 |
+
tags:
|
| 4 |
+
- sentence-transformers
|
| 5 |
+
- feature-extraction
|
| 6 |
+
- sentence-similarity
|
| 7 |
+
---
|
| 8 |
+
# multi-QA_v1-mpnet-asymmetric-A
|
| 9 |
+
This is mpnet-base model trained on 1B+ question - answer pairs. 2 separate models were used for training. This model was used to encode Answers.
|
| 10 |
+
## Usage
|
| 11 |
+
The model can be used for semantic-search in conjunction with question model : [multi-QA_v1-mpnet-asymmetric-Q](https://huggingface.co/flax-sentence-embeddings/multi-QA_v1-mpnet-asymmetric-Q)
|
| 12 |
+
Output vectors are normalized and mean pooling used during training.
|
| 13 |
+
|