Instructions to use facebook/bart-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/bart-large with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="facebook/bart-large")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("facebook/bart-large") model = AutoModel.from_pretrained("facebook/bart-large") - Inference
- Notebooks
- Google Colab
- Kaggle
About filling multi-token masks.
#7
by luoxlong - opened
If I want it to just fill one token to "mask" token, what should I do?
A mask filling example is :
https://huggingface.co/docs/transformers/model_doc/bart#mask-filling
The facebook/bart-base and facebook/bart-large checkpoints fill multi-token masks (
However, can it fill just one token for one "mask" token?
For "I love the mask apple", I want it to be "I love the red apple", not "I love the big and tasty apple".