add readme and pooling
Browse files- 1_Pooling/config.json +10 -0
- README.md +5 -4
1_Pooling/config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 768,
|
3 |
+
"pooling_mode_cls_token": true,
|
4 |
+
"pooling_mode_mean_tokens": false,
|
5 |
+
"pooling_mode_max_tokens": false,
|
6 |
+
"pooling_mode_mean_sqrt_len_tokens": false,
|
7 |
+
"pooling_mode_weightedmean_tokens": false,
|
8 |
+
"pooling_mode_lasttoken": false,
|
9 |
+
"include_prompt": true
|
10 |
+
}
|
README.md
CHANGED
@@ -9,11 +9,13 @@ tags:
|
|
9 |
|
10 |
---
|
11 |
|
12 |
-
#
|
13 |
|
14 |
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.
|
15 |
|
16 |
-
|
|
|
|
|
17 |
|
18 |
## Usage (Sentence-Transformers)
|
19 |
|
@@ -120,5 +122,4 @@ SentenceTransformer(
|
|
120 |
```
|
121 |
|
122 |
## Citing & Authors
|
123 |
-
|
124 |
-
<!--- Describe where people can find more information -->
|
|
|
9 |
|
10 |
---
|
11 |
|
12 |
+
# FISMWASP Autoencoder 400k-e2
|
13 |
|
14 |
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.
|
15 |
|
16 |
+
This is an embedding model that makes it possible to organise German language and technical specifications in a vector space without vector overlays. It is an S-bert model with the TSDAE architecture. The model was developed by André Osyguß from Medienwerft with the help of colleagues from FIS ASP and FIS.
|
17 |
+
|
18 |
+
This model was trained with technical ticket data. Over four hundred thousand sentences were used for training in order to achieve optimal results.
|
19 |
|
20 |
## Usage (Sentence-Transformers)
|
21 |
|
|
|
122 |
```
|
123 |
|
124 |
## Citing & Authors
|
125 |
+
authored by André Osyguß
|
|