Update README.md
Browse files
README.md
CHANGED
@@ -11,9 +11,11 @@ license: lgpl-3.0
|
|
11 |
library_name: sentence-transformers
|
12 |
datasets:
|
13 |
- radlab/polish-sts-dataset
|
|
|
|
|
14 |
---
|
15 |
|
16 |
-
# polish-
|
17 |
|
18 |
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.
|
19 |
|
@@ -33,7 +35,7 @@ Then you can use the model like this:
|
|
33 |
from sentence_transformers import SentenceTransformer
|
34 |
sentences = ["Ala ma kota", "Ala ma psa"]
|
35 |
|
36 |
-
model = SentenceTransformer('radlab/polish-
|
37 |
embeddings = model.encode(sentences)
|
38 |
print(embeddings)
|
39 |
```
|
@@ -58,8 +60,8 @@ def mean_pooling(model_output, attention_mask):
|
|
58 |
sentences = ['Ala ma kota', 'Ala ma psa']
|
59 |
|
60 |
# Load model from HuggingFace Hub
|
61 |
-
tokenizer = AutoTokenizer.from_pretrained('radlab/polish-
|
62 |
-
model = AutoModel.from_pretrained('radlab/polish-
|
63 |
|
64 |
# Tokenize sentences
|
65 |
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
|
|
|
11 |
library_name: sentence-transformers
|
12 |
datasets:
|
13 |
- radlab/polish-sts-dataset
|
14 |
+
models:
|
15 |
+
- sdadas/polish-roberta-large-v2
|
16 |
---
|
17 |
|
18 |
+
# radlab/polish-sts-v2
|
19 |
|
20 |
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.
|
21 |
|
|
|
35 |
from sentence_transformers import SentenceTransformer
|
36 |
sentences = ["Ala ma kota", "Ala ma psa"]
|
37 |
|
38 |
+
model = SentenceTransformer('radlab/polish-sts-v2')
|
39 |
embeddings = model.encode(sentences)
|
40 |
print(embeddings)
|
41 |
```
|
|
|
60 |
sentences = ['Ala ma kota', 'Ala ma psa']
|
61 |
|
62 |
# Load model from HuggingFace Hub
|
63 |
+
tokenizer = AutoTokenizer.from_pretrained('radlab/polish-sts-v2')
|
64 |
+
model = AutoModel.from_pretrained('radlab/polish-sts-v2')
|
65 |
|
66 |
# Tokenize sentences
|
67 |
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
|