Instructions to use google/flan-ul2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/flan-ul2 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("google/flan-ul2") model = AutoModelForMultimodalLM.from_pretrained("google/flan-ul2") - Notebooks
- Google Colab
- Kaggle
AutoModelForConditionalGeneration -> T5ForConditionalGeneration
#3
by gojiteji - opened
It seems that AutoModelForConditionalGeneration doesn't exist in HF API, so I changed to T5ForConditionalGeneration based on config.json .
Thanks a mile for the fix!
ybelkada changed pull request status to merged