Feature Extraction
Transformers
PyTorch
Safetensors
English
bert
mteb
Eval Results (legacy)
text-embeddings-inference
Instructions to use fresha/e5-large-v2-endpoint with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use fresha/e5-large-v2-endpoint with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="fresha/e5-large-v2-endpoint")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("fresha/e5-large-v2-endpoint") model = AutoModel.from_pretrained("fresha/e5-large-v2-endpoint") - Notebooks
- Google Colab
- Kaggle
Hans Elias J commited on
Commit ·
ce64906
1
Parent(s): 0996185
fix norm
Browse files- handler.py +2 -2
handler.py
CHANGED
|
@@ -30,7 +30,7 @@ class EndpointHandler():
|
|
| 30 |
|
| 31 |
outputs = self.model(**batch_dict)
|
| 32 |
|
| 33 |
-
embeddings = average_pool(outputs.last_hidden_state, batch_dict['attention_mask'])
|
| 34 |
-
embeddings = F.normalize(embeddings, p=2, dim=1)
|
| 35 |
|
| 36 |
return embeddings
|
|
|
|
| 30 |
|
| 31 |
outputs = self.model(**batch_dict)
|
| 32 |
|
| 33 |
+
embeddings = average_pool(outputs.last_hidden_state, batch_dict['attention_mask'])
|
| 34 |
+
embeddings = F.normalize(embeddings, p=2, dim=1).tolist()
|
| 35 |
|
| 36 |
return embeddings
|