Instructions to use Inria-CEDAR/GrailQAT5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Inria-CEDAR/GrailQAT5B with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Inria-CEDAR/GrailQAT5B") model = AutoModelForSeq2SeqLM.from_pretrained("Inria-CEDAR/GrailQAT5B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from Inria-CEDAR/GrailQAT5B: direct link, hf CLI and curl.
- Browser
- Download file 1.16 GB
-
https://huggingface.co/Inria-CEDAR/GrailQAT5B/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://Inria-CEDAR/GrailQAT5B/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/Inria-CEDAR/GrailQAT5B/resolve/main/pytorch_model.bin
1.16 GB
- Xet hash:
- 7353d0256c160c8e08b439fee52ef8c7f8cb5fa0ee3bfc967fc36624b4edc070
- Size of remote file:
- 1.16 GB
- SHA256:
- 8bedaada12689a7402f0e1f30317095cddca9fcb5031b1dbdcac86a13e8d0e0c
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.