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 model
Browse filesPer https://www.sbert.net/examples/applications/semantic-search/README.html, Imitating https://colab.research.google.com/github/UKPLab/sentence-transformers/blob/master/examples/applications/retrieve_rerank/retrieve_rerank_simple_wikipedia.ipynb#scrollTo=D_hDi8KzNgMM
- handler.py +2 -2
handler.py
CHANGED
|
@@ -10,8 +10,8 @@ def mean_pooling(model_output, attention_mask):
|
|
| 10 |
|
| 11 |
class EndpointHandler():
|
| 12 |
def __init__(self, path=""):
|
| 13 |
-
self.tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/
|
| 14 |
-
self.model = AutoModel.from_pretrained('sentence-transformers/
|
| 15 |
|
| 16 |
def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
|
| 17 |
"""
|
|
|
|
| 10 |
|
| 11 |
class EndpointHandler():
|
| 12 |
def __init__(self, path=""):
|
| 13 |
+
self.tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/multi-qa-MiniLM-L6-cos-v1')
|
| 14 |
+
self.model = AutoModel.from_pretrained('sentence-transformers/multi-qa-MiniLM-L6-cos-v1')
|
| 15 |
|
| 16 |
def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
|
| 17 |
"""
|