Instructions to use hkunlp/T5_large_prefix_all_tasks_2upsample2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hkunlp/T5_large_prefix_all_tasks_2upsample2 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("hkunlp/T5_large_prefix_all_tasks_2upsample2") model = AutoModel.from_pretrained("hkunlp/T5_large_prefix_all_tasks_2upsample2") - Notebooks
- Google Colab
- Kaggle
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
This is the ckpt of prefix-tuning model we trained on 21 tasks using a upsampling temp of 2. Note: The prefix module is large due to the fact we keep the re-param weight and didn't compress it to make it more original and extendable for researchers.
- Downloads last month
- 7
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support