Instructions to use Jzz/FidicBERT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Jzz/FidicBERT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="Jzz/FidicBERT")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("Jzz/FidicBERT") model = AutoModelForMaskedLM.from_pretrained("Jzz/FidicBERT", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download optimizer.pt from Jzz/FidicBERT: direct link, hf CLI and curl.
- Browser
- Download file 998 MB
-
https://huggingface.co/Jzz/FidicBERT/resolve/main/optimizer.pt
- Command line
-
hf download hf://Jzz/FidicBERT/optimizer.pt
-
curl -L -o optimizer.pt https://huggingface.co/Jzz/FidicBERT/resolve/main/optimizer.pt
998 MB
- Xet hash:
- 7fea5a2a867eb4f0a8edeb5ed4da2b158b29c169ec0d1fa8a1b1dae7583df3c7
- Size of remote file:
- 998 MB
- SHA256:
- bb290d3df9bd1d92466eee96236d9b172db9e85631a098cc7e2b9cc9bf170fb7
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.