Instructions to use jpohhhh/biencoder_embedding with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jpohhhh/biencoder_embedding with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="jpohhhh/biencoder_embedding")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("jpohhhh/biencoder_embedding") model = AutoModel.from_pretrained("jpohhhh/biencoder_embedding", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update handler.py
Browse files- handler.py +1 -1
handler.py
CHANGED
|
@@ -17,5 +17,5 @@ class EndpointHandler():
|
|
| 17 |
A :obj:`list` | `dict`: will be serialized and returned
|
| 18 |
"""
|
| 19 |
sentences = data.pop("inputs",data)
|
| 20 |
-
embeddings = self.model.encode(sentences, batch_size=100)
|
| 21 |
return embeddings.tolist()
|
|
|
|
| 17 |
A :obj:`list` | `dict`: will be serialized and returned
|
| 18 |
"""
|
| 19 |
sentences = data.pop("inputs",data)
|
| 20 |
+
embeddings = self.model.encode(sentences, batch_size=100, device="cuda")
|
| 21 |
return embeddings.tolist()
|