Instructions to use jrc-ai/PreDA-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jrc-ai/PreDA-base with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("jrc-ai/PreDA-base") model = AutoModelForSeq2SeqLM.from_pretrained("jrc-ai/PreDA-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preda_architecture_digram.png from jrc-ai/PreDA-base: direct link, hf CLI and curl.
- Browser
- Download file 1.28 MB
-
https://huggingface.co/jrc-ai/PreDA-base/resolve/main/preda_architecture_digram.png
- Command line
-
hf download hf://jrc-ai/PreDA-base/preda_architecture_digram.png
-
curl -L -o preda_architecture_digram.png https://huggingface.co/jrc-ai/PreDA-base/resolve/main/preda_architecture_digram.png
1.28 MB

- Xet hash:
- d25c76a53a3a0655dfb39cedc34688b0dee59b2dbd12d87d89cec19a16cef177
- Size of remote file:
- 1.28 MB
- SHA256:
- 73082e0372ef5fbd977c8219c669f176b78536b834ea8381901dc9a8786c0392
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.