Update README.md
Browse files
README.md
CHANGED
@@ -6,14 +6,22 @@ tags:
|
|
6 |
- feature-extraction
|
7 |
- sentence-similarity
|
8 |
- transformers
|
9 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
---
|
11 |
|
12 |
# atasoglu/distilbert-base-turkish-cased-nli-stsb-tr
|
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 |
|
@@ -76,9 +84,14 @@ print(sentence_embeddings)
|
|
76 |
|
77 |
## Evaluation Results
|
78 |
|
79 |
-
|
80 |
|
81 |
-
|
|
|
|
|
|
|
|
|
|
|
82 |
|
83 |
|
84 |
## Training
|
|
|
6 |
- feature-extraction
|
7 |
- sentence-similarity
|
8 |
- transformers
|
9 |
+
license: mit
|
10 |
+
datasets:
|
11 |
+
- nli_tr
|
12 |
+
- emrecan/stsb-mt-turkish
|
13 |
+
language:
|
14 |
+
- tr
|
15 |
+
base_model: dbmdz/distilbert-base-turkish-cased
|
16 |
---
|
17 |
|
18 |
# atasoglu/distilbert-base-turkish-cased-nli-stsb-tr
|
19 |
|
20 |
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.
|
21 |
|
22 |
+
This model was adapted from [dbmdz/distilbert-base-turkish-cased](https://huggingface.co/dbmdz/distilbert-base-turkish-cased) and fine-tuned on these datasets:
|
23 |
+
- [nli_tr](https://huggingface.co/datasets/nli_tr)
|
24 |
+
- [emrecan/stsb-mt-turkish](https://huggingface.co/datasets/emrecan/stsb-mt-turkish)
|
25 |
|
26 |
## Usage (Sentence-Transformers)
|
27 |
|
|
|
84 |
|
85 |
## Evaluation Results
|
86 |
|
87 |
+
Achieved results on the [STS-b](https://huggingface.co/datasets/emrecan/stsb-mt-turkish) test split are given below:
|
88 |
|
89 |
+
```txt
|
90 |
+
Cosine-Similarity : Pearson: 0.8167 Spearman: 0.8158
|
91 |
+
Manhattan-Distance: Pearson: 0.7540 Spearman: 0.7463
|
92 |
+
Euclidean-Distance: Pearson: 0.7545 Spearman: 0.7470
|
93 |
+
Dot-Product-Similarity: Pearson: 0.6543 Spearman: 0.6571
|
94 |
+
```
|
95 |
|
96 |
|
97 |
## Training
|