Instructions to use allenai/PRIMERA-wcep with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use allenai/PRIMERA-wcep with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("allenai/PRIMERA-wcep") model = AutoModelForSeq2SeqLM.from_pretrained("allenai/PRIMERA-wcep") - Notebooks
- Google Colab
- Kaggle
Update config.json
#3
by johngiorgi - opened
Add num_beams: 5 and no_repeat_ngram_size: 3 to the config as defaults. Like allenai/PRIMERA-multinews and allenai/PRIMERA-multixscience, this are required to get scores closer to the scores reported in the original PRIMERA paper.
@armanc will you merge if this is okay?
@johngiorgi merged :)
soldni changed pull request status to merged