Feature Extraction
Transformers
Safetensors
sentence-transformers
PyTorch
English
bert_retriever
bert
dense-retrieval
semantic-search
information-retrieval
faiss
retrieval
semantic
embeddings
custom_code
Instructions to use Innovatewithapple/bert-dense-retriever with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Innovatewithapple/bert-dense-retriever with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Innovatewithapple/bert-dense-retriever", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Innovatewithapple/bert-dense-retriever", trust_remote_code=True, device_map="auto") - sentence-transformers
How to use Innovatewithapple/bert-dense-retriever with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Innovatewithapple/bert-dense-retriever", trust_remote_code=True) 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
Add auto_map for custom model loading
Browse files- config.json +5 -1
config.json
CHANGED
|
@@ -7,5 +7,9 @@
|
|
| 7 |
"dtype": "float32",
|
| 8 |
"hidden_size": 768,
|
| 9 |
"model_type": "bert_retriever",
|
| 10 |
-
"transformers_version": "4.57.6"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
}
|
|
|
|
| 7 |
"dtype": "float32",
|
| 8 |
"hidden_size": 768,
|
| 9 |
"model_type": "bert_retriever",
|
| 10 |
+
"transformers_version": "4.57.6",
|
| 11 |
+
"auto_map": {
|
| 12 |
+
"AutoConfig": "configuration_bert_retriever.BertRetrieverConfig",
|
| 13 |
+
"AutoModel": "modeling_bert_retriever.BertRetriever"
|
| 14 |
+
}
|
| 15 |
}
|