Feature Extraction
Transformers
PyTorch
Safetensors
Hebrew
bert
custom_code
text-embeddings-inference
Instructions to use dicta-il/dictabert-joint with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dicta-il/dictabert-joint with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="dicta-il/dictabert-joint", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("dicta-il/dictabert-joint", trust_remote_code=True) model = AutoModel.from_pretrained("dicta-il/dictabert-joint", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
add sentence-transformers(or/and gguf) embedding model version
#4
by benayat - opened
Since this joint model has multiple capabilities and can capture the "meaning" of each sentence in hebrew, an embedding model from that will make RAG application in Hebrew possible, and Simillarity search will be much better than the existing english embedding models.
is that possible?
Yes, a model like that is in the works :)
We are hoping to release it in the coming months.
benayat changed discussion status to closed