Instructions to use sinequa/vectorizer.hazelnut with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sinequa/vectorizer.hazelnut with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("sinequa/vectorizer.hazelnut") model = AutoModelForMaskedLM.from_pretrained("sinequa/vectorizer.hazelnut", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download 1_Pooling/config.json from sinequa/vectorizer.hazelnut: direct link, hf CLI and curl.
- Browser
- Download file 196 Bytes
-
https://huggingface.co/sinequa/vectorizer.hazelnut/resolve/refs%2Fpr%2F5/1_Pooling/config.json
- Command line
-
hf download hf://sinequa/vectorizer.hazelnut@refs/pr/5/1_Pooling/config.json
-
curl -L -o config.json https://huggingface.co/sinequa/vectorizer.hazelnut/resolve/refs%2Fpr%2F5/1_Pooling/config.json
196 Bytes
| { | |
| "word_embedding_dimension": 384, | |
| "pooling_mode_cls_token": false, | |
| "pooling_mode_mean_tokens": true, | |
| "pooling_mode_max_tokens": false, | |
| "pooling_mode_mean_sqrt_len_tokens": false | |
| } |