Instructions to use google/switch-base-8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/switch-base-8 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("google/switch-base-8") model = AutoModelForSeq2SeqLM.from_pretrained("google/switch-base-8", device_map="auto") - Notebooks
- Google Colab
- Kaggle
It seems there is no 'SwitchTransformersConditionalGeneration', but SwitchTransformersForConditionalGeneration
#3
by VIArchitect - opened
In the model card, the GPU example imports SwitchTransformersConditionalGeneration.
But it seems that there's no SwitchTransformersConditionalGeneration module, but SwitchTransformersForConditionalGeneration only exist.
Are those two things convertible?
Thanks for your issue @VIArchitect
I have just updated the model card! Thanks
VIArchitect changed discussion status to closed