Instructions to use sinequa/vectorizer-v1-S-en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sinequa/vectorizer-v1-S-en with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("sinequa/vectorizer-v1-S-en") model = AutoModel.from_pretrained("sinequa/vectorizer-v1-S-en") - Notebooks
- Google Colab
- Kaggle
Add "pooler-output" to sinequa.metadata.json
#3
by boris-f - opened
Following the Pooling strategy changes for Sinequa model packagings, we enforce for this vectorizer the use of the model 'pooler_output' instead of the strategy defined in '1_Pooling/config.json'
boris-f changed pull request status to merged