Instructions to use google/flan-t5-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/flan-t5-base with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("google/flan-t5-base") model = AutoModelForSeq2SeqLM.from_pretrained("google/flan-t5-base") - Notebooks
- Google Colab
- Kaggle
Wrong screenshot in "Testing Data, Factors & Metrics" section
#6
by attekei - opened
Hi, in the model card you use a screenshot from this paper for showing model metrics for different task sets. Unfortunately, the metrics in the screenshot are only for Flan-PaLM, which is Google's proprietary model. Please instead use the attached table (from page 11) which includes T5 models as well.
wow thanks for noticing! Will open a PR soon ;)
Awesome :) Seems that you applied this already to all model variants – great stuff.
attekei changed discussion status to closed
Yep! thanks for noticing the nit ;)
