Instructions to use deepset/bert-small-mm_retrieval-table_encoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use deepset/bert-small-mm_retrieval-table_encoder with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, DPRContextEncoder tokenizer = AutoTokenizer.from_pretrained("deepset/bert-small-mm_retrieval-table_encoder") model = DPRContextEncoder.from_pretrained("deepset/bert-small-mm_retrieval-table_encoder", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from deepset/bert-small-mm_retrieval-table_encoder: direct link, hf CLI and curl.
- Browser
- Download file 115 MB
-
https://huggingface.co/deepset/bert-small-mm_retrieval-table_encoder/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://deepset/bert-small-mm_retrieval-table_encoder/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/deepset/bert-small-mm_retrieval-table_encoder/resolve/main/pytorch_model.bin
115 MB
- Xet hash:
- cac65d985d731ea7de6ba80108debb3d16e616fa780d3ff752d0ee8015e142de
- Size of remote file:
- 115 MB
- SHA256:
- 0eaaa7e0e15bc287f18e18c223070b11c2169930913795a84242cec42bcd9b53
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.