Update README.md
Browse files
README.md
CHANGED
@@ -22,7 +22,7 @@ The model intended to be used for encoding sentences or short paragraphs. Given
|
|
22 |
The model was trained on a random collection of **English** sentences from Wikipedia: [Training data file](https://huggingface.co/datasets/princeton-nlp/datasets-for-simcse/resolve/main/wiki1m_for_simcse.txt)
|
23 |
|
24 |
# Model Usage
|
25 |
-
|
26 |
|
27 |
```python
|
28 |
from transformers import AutoTokenizer, AutoModel
|
@@ -69,7 +69,7 @@ cos_sim = sim(embeddings.unsqueeze(1),
|
|
69 |
print(f"Distance: {cos_sim[0,1].detach().item()}")
|
70 |
```
|
71 |
|
72 |
-
|
73 |
|
74 |
```python
|
75 |
from transformers import AutoTokenizer, AutoModel
|
@@ -147,7 +147,7 @@ umap_plot.points(umap_model, labels = np.array(classes),theme='fire')
|
|
147 |
![UMAP Cluster](https://raw.githubusercontent.com/TJKlein/tjklein.github.io/master/images/miCSE_UMAP_small2.png)
|
148 |
|
149 |
|
150 |
-
|
151 |
|
152 |
```python
|
153 |
from sentence_transformers import SentenceTransformer, util
|
|
|
22 |
The model was trained on a random collection of **English** sentences from Wikipedia: [Training data file](https://huggingface.co/datasets/princeton-nlp/datasets-for-simcse/resolve/main/wiki1m_for_simcse.txt)
|
23 |
|
24 |
# Model Usage
|
25 |
+
### Example 1) - Sentence Similarity
|
26 |
|
27 |
```python
|
28 |
from transformers import AutoTokenizer, AutoModel
|
|
|
69 |
print(f"Distance: {cos_sim[0,1].detach().item()}")
|
70 |
```
|
71 |
|
72 |
+
### Example 2) - Clustering
|
73 |
|
74 |
```python
|
75 |
from transformers import AutoTokenizer, AutoModel
|
|
|
147 |
![UMAP Cluster](https://raw.githubusercontent.com/TJKlein/tjklein.github.io/master/images/miCSE_UMAP_small2.png)
|
148 |
|
149 |
|
150 |
+
### Example 3) - Using [SentenceTransformers](https://www.sbert.net/)
|
151 |
|
152 |
```python
|
153 |
from sentence_transformers import SentenceTransformer, util
|