Update README.md
Browse files
README.md
CHANGED
|
@@ -16,23 +16,14 @@ tags:
|
|
| 16 |
widget:
|
| 17 |
- source_sentence: "This is a sample source sentence." # Ensure this is not empty
|
| 18 |
target_sentence: "This is a sample target sentence." # Ensure this is not empty
|
| 19 |
-
|
| 20 |
|
| 21 |
|
| 22 |
# SentenceTransformer based on microsoft/mpnet-base
|
| 23 |
|
| 24 |
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-base) on the [reranking_1](https://huggingface.co/datasets/mteb/askubuntudupquestions-reranking), [retrival_1](https://huggingface.co/datasets/mteb/arguana) and [sts_1](https://huggingface.co/datasets/mteb/biosses-sts) datasets. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
|
| 25 |
|
| 26 |
-
## Model Details
|
| 27 |
|
| 28 |
-
### Model Description
|
| 29 |
-
- **Model Type:** Sentence Transformer
|
| 30 |
-
- **Base model:** [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-base) <!-- at revision 6996ce1e91bd2a9c7d7f61daec37463394f73f09 -->
|
| 31 |
-
- **Maximum Sequence Length:** 512 tokens
|
| 32 |
-
- **Output Dimensionality:** 768 tokens
|
| 33 |
-
- **Similarity Function:** Cosine Similarity
|
| 34 |
-
- **Language:** en
|
| 35 |
-
<!-- - **License:** Unknown -->
|
| 36 |
|
| 37 |
### Model Sources
|
| 38 |
|
|
@@ -72,12 +63,4 @@ print(embeddings.shape)
|
|
| 72 |
similarities = model.similarity(embeddings, embeddings)
|
| 73 |
print(similarities.shape)
|
| 74 |
# [3, 3]
|
| 75 |
-
```
|
| 76 |
-
|
| 77 |
-
<!--
|
| 78 |
-
### Direct Usage (Transformers)
|
| 79 |
-
|
| 80 |
-
<details><summary>Click to see the direct usage in Transformers</summary>
|
| 81 |
-
|
| 82 |
-
</details>
|
| 83 |
-
-->
|
|
|
|
| 16 |
widget:
|
| 17 |
- source_sentence: "This is a sample source sentence." # Ensure this is not empty
|
| 18 |
target_sentence: "This is a sample target sentence." # Ensure this is not empty
|
| 19 |
+
---
|
| 20 |
|
| 21 |
|
| 22 |
# SentenceTransformer based on microsoft/mpnet-base
|
| 23 |
|
| 24 |
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-base) on the [reranking_1](https://huggingface.co/datasets/mteb/askubuntudupquestions-reranking), [retrival_1](https://huggingface.co/datasets/mteb/arguana) and [sts_1](https://huggingface.co/datasets/mteb/biosses-sts) datasets. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
|
| 25 |
|
|
|
|
| 26 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
|
| 28 |
### Model Sources
|
| 29 |
|
|
|
|
| 63 |
similarities = model.similarity(embeddings, embeddings)
|
| 64 |
print(similarities.shape)
|
| 65 |
# [3, 3]
|
| 66 |
+
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|