Sentence Similarity
sentence-transformers
Safetensors
Transformers
bert
feature-extraction
custom_code
text-embeddings-inference
Instructions to use sentence-transformers-testing/st-bert-base-uncased with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use sentence-transformers-testing/st-bert-base-uncased with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("sentence-transformers-testing/st-bert-base-uncased", trust_remote_code=True) sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Transformers
How to use sentence-transformers-testing/st-bert-base-uncased with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("sentence-transformers-testing/st-bert-base-uncased", trust_remote_code=True) model = AutoModel.from_pretrained("sentence-transformers-testing/st-bert-base-uncased", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add custom configuration file
Browse files- custom_configuration.py +7 -0
custom_configuration.py
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
from transformers import BertConfig
|
| 3 |
+
|
| 4 |
+
class CustomBertConfig(BertConfig):
|
| 5 |
+
def __init__(self, *args, **kwargs):
|
| 6 |
+
super().__init__(*args, **kwargs)
|
| 7 |
+
self.custom_config = "This is a custom configuration class"
|