jhgan commited on
Commit
7bd3416
β€’
1 Parent(s): 2dc8841

updated README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -9
README.md CHANGED
@@ -6,7 +6,7 @@ tags:
6
  - sentence-similarity
7
  ---
8
 
9
- # {MODEL_NAME}
10
 
11
  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.
12
 
@@ -14,19 +14,19 @@ This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentence
14
 
15
  ## Usage (Sentence-Transformers)
16
 
17
- Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
18
 
19
  ```
20
- pip install -U sentence-transformers
21
  ```
22
 
23
  Then you can use the model like this:
24
 
25
  ```python
26
  from sentence_transformers import SentenceTransformer
27
- sentences = ["This is an example sentence", "Each sentence is converted"]
28
 
29
- model = SentenceTransformer('{MODEL_NAME}')
30
  embeddings = model.encode(sentences)
31
  print(embeddings)
32
  ```
@@ -35,10 +35,16 @@ print(embeddings)
35
 
36
  ## Evaluation Results
37
 
38
- <!--- Describe how your model was evaluated -->
39
-
40
- For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
41
 
 
 
 
 
 
 
 
 
42
 
43
  ## Training
44
  The model was trained with the parameters:
@@ -83,4 +89,4 @@ SentenceTransformer(
83
 
84
  ## Citing & Authors
85
 
86
- <!--- Describe where people can find more information -->
 
6
  - sentence-similarity
7
  ---
8
 
9
+ # ko-sbert-sts
10
 
11
  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.
12
 
 
14
 
15
  ## Usage (Sentence-Transformers)
16
 
17
+ λͺ¨λΈμ„ μ‚¬μš©ν•˜κΈ° μœ„ν•΄μ„œλŠ” `ko-sentence-transformers` λ₯Ό μ„€μΉ˜ν•΄μ•Ό ν•©λ‹ˆλ‹€.
18
 
19
  ```
20
+ pip install -U ko-sentence-transformers
21
  ```
22
 
23
  Then you can use the model like this:
24
 
25
  ```python
26
  from sentence_transformers import SentenceTransformer
27
+ sentences = ["μ•ˆλ…•ν•˜μ„Έμš”?", "ν•œκ΅­μ–΄ λ¬Έμž₯ μž„λ² λ”©μ„ μœ„ν•œ λ²„νŠΈ λͺ¨λΈμž…λ‹ˆλ‹€."]
28
 
29
+ model = SentenceTransformer('ko-sbert-sts')
30
  embeddings = model.encode(sentences)
31
  print(embeddings)
32
  ```
 
35
 
36
  ## Evaluation Results
37
 
38
+ KorSTS ν•™μŠ΅ λ°μ΄ν„°μ…‹μœΌλ‘œ ν•™μŠ΅ν•œ ν›„ KorSTS 평가 λ°μ΄ν„°μ…‹μœΌλ‘œ ν‰κ°€ν•œ κ²°κ³Όμž…λ‹ˆλ‹€.
 
 
39
 
40
+ - Cosine Pearson: 80.79
41
+ - Cosine Spearman: 79.01
42
+ - Euclidean Pearson: 78.03
43
+ - Euclidean Spearman: 77.31
44
+ - Manhattan Pearson: 78.08
45
+ - Manhattan Spearman: 77.35
46
+ - Dot Pearson: 75.96
47
+ - Dot Spearman: 75.20
48
 
49
  ## Training
50
  The model was trained with the parameters:
 
89
 
90
  ## Citing & Authors
91
 
92
+ <!--- Describe where people can find more information -->