Zero-Shot Classification
PyTorch
Transformers
sentence-transformers
English
zeroshot_classifier
bert
feature-extraction
Instructions to use claritylab/zero-shot-implicit-bi-encoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use claritylab/zero-shot-implicit-bi-encoder with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-classification", model="claritylab/zero-shot-implicit-bi-encoder")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("claritylab/zero-shot-implicit-bi-encoder") model = AutoModel.from_pretrained("claritylab/zero-shot-implicit-bi-encoder") - sentence-transformers
How to use claritylab/zero-shot-implicit-bi-encoder with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("claritylab/zero-shot-implicit-bi-encoder") 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
|
@@ -43,8 +43,8 @@ You can use the model like this:
|
|
| 43 |
>>> 'Search Screening Event'
|
| 44 |
>>> ]
|
| 45 |
>>> aspect = 'intent'
|
| 46 |
-
>>>
|
| 47 |
-
>>> text = f'{aspect} {
|
| 48 |
|
| 49 |
>>> text_embed = model.encode(text)
|
| 50 |
>>> label_embeds = model.encode(labels)
|
|
|
|
| 43 |
>>> 'Search Screening Event'
|
| 44 |
>>> ]
|
| 45 |
>>> aspect = 'intent'
|
| 46 |
+
>>> aspect_sep_token = model.tokenizer.additional_special_tokens[0]
|
| 47 |
+
>>> text = f'{aspect} {aspect_sep_token} {text}'
|
| 48 |
|
| 49 |
>>> text_embed = model.encode(text)
|
| 50 |
>>> label_embeds = model.encode(labels)
|