Instructions to use Decycle/simcse_longembed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Decycle/simcse_longembed with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("Decycle/simcse_longembed") model = AutoModel.from_pretrained("Decycle/simcse_longembed") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 0bd85a3da3c34ac9a81f73ddc83ade8a0b6348d86d4919b9ae9c092f7d470e0a
- Size of remote file:
- 499 MB
- SHA256:
- 530866d7b2fb9dd420e26c59aa67681202fba99813608f60b1b0571d9008e417
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.