Add custom notebook.ipynb
#5
by
MaximilianSchambach
- opened
Thanks, looks good to me. In the metadata, there is "gpuType": "T4", but I do not know what is the consequence of that. We use a 2048 context size, so that should also be fine.
I copied this from the default HF notebook. I just tested the inference on Colab with T4 and it works fine.
MaximilianSchambach
changed pull request status to
merged