Zero-Shot Classification
PyTorch
Transformers
sentence-transformers
English
zeroshot_classifier
bert
text-classification
Instructions to use claritylab/zero-shot-implicit-binary-bert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use claritylab/zero-shot-implicit-binary-bert with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-classification", model="claritylab/zero-shot-implicit-binary-bert")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("claritylab/zero-shot-implicit-binary-bert") model = AutoModelForSequenceClassification.from_pretrained("claritylab/zero-shot-implicit-binary-bert", device_map="auto") - sentence-transformers
How to use claritylab/zero-shot-implicit-binary-bert with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("claritylab/zero-shot-implicit-binary-bert") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -32,7 +32,8 @@ You can use the model like this:
|
|
| 32 |
>>> 'Add To Playlist', 'Book Restaurant', 'Get Weather', 'Play Music', 'Rate Book', 'Search Creative Work',
|
| 33 |
>>> 'Search Screening Event'
|
| 34 |
>>> ]
|
| 35 |
-
>>>
|
|
|
|
| 36 |
>>> logits = model.predict(query, apply_softmax=True)
|
| 37 |
>>> print(logits)
|
| 38 |
|
|
|
|
| 32 |
>>> 'Add To Playlist', 'Book Restaurant', 'Get Weather', 'Play Music', 'Rate Book', 'Search Creative Work',
|
| 33 |
>>> 'Search Screening Event'
|
| 34 |
>>> ]
|
| 35 |
+
>>> aspect = 'intent'
|
| 36 |
+
>>> query = [[text, f'{lb} {aspect}'] for lb in labels]
|
| 37 |
>>> logits = model.predict(query, apply_softmax=True)
|
| 38 |
>>> print(logits)
|
| 39 |
|