Update README.md
Browse files
README.md
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
---
|
|
|
|
| 2 |
library_name: sentence-transformers
|
| 3 |
pipeline_tag: sentence-similarity
|
| 4 |
tags:
|
|
@@ -21,6 +22,8 @@ language:
|
|
| 21 |
|
| 22 |
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.
|
| 23 |
|
|
|
|
|
|
|
| 24 |
- pretrained & finetuned at context length 16384
|
| 25 |
- This model is a "v1" and we may make improved versions in the future. Or, we may not.
|
| 26 |
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: BEE-spoke-data/mega-encoder-small-16k-v1
|
| 3 |
library_name: sentence-transformers
|
| 4 |
pipeline_tag: sentence-similarity
|
| 5 |
tags:
|
|
|
|
| 22 |
|
| 23 |
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.
|
| 24 |
|
| 25 |
+
- this model's primary use case is meant to be long-document similarity, i.e. computing embeddings of long documents and comparing those.
|
| 26 |
+
- check out the training dataset `pszemraj/synthetic-text-similarity` for details
|
| 27 |
- pretrained & finetuned at context length 16384
|
| 28 |
- This model is a "v1" and we may make improved versions in the future. Or, we may not.
|
| 29 |
|