Instructions to use sinequa/vectorizer-v1-S-multilingual with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sinequa/vectorizer-v1-S-multilingual with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("sinequa/vectorizer-v1-S-multilingual") model = AutoModel.from_pretrained("sinequa/vectorizer-v1-S-multilingual", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download reduction_layer.bin from sinequa/vectorizer-v1-S-multilingual: direct link, hf CLI and curl.
- Browser
- Download file 526 kB
-
https://huggingface.co/sinequa/vectorizer-v1-S-multilingual/resolve/main/reduction_layer.bin
- Command line
-
hf download hf://sinequa/vectorizer-v1-S-multilingual/reduction_layer.bin
-
curl -L -o reduction_layer.bin https://huggingface.co/sinequa/vectorizer-v1-S-multilingual/resolve/main/reduction_layer.bin
526 kB
- Xet hash:
- e15c2344f26ff10b1c2e872a520326394aff07565b2be4c810c311faf76a5aa8
- Size of remote file:
- 526 kB
- SHA256:
- 84d3da79f783f981db2e2ff48de325475d6f30d96dc53fcef2ef11f438444d3e
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.