Instructions to use bigscience/T0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bigscience/T0 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("bigscience/T0") model = AutoModelForSeq2SeqLM.from_pretrained("bigscience/T0") - Notebooks
- Google Colab
- Kaggle
Filling in masked tokens?
#1
by latitude - opened
Is there a way to use the Inference API for T0pp to fill in multiple tokens (including an unknown number of tokens) that have been masked (rather than question answering, which seems to be the default behavior)? If not, can you show an example of how to do it in my own code?