London Lowmanstone

From [this](https://stackoverflow.com/a/65993776/5049813), adding `%pip install numpy==1.19.5` just before the code block that does the prediction seems to have fixed the issue.

You may need to restart the notebook after running this line in order to have it take effect. (However, it should warn you of this automatically.)

Looks like this issue has been noted [here](https://gist.github.com/W4ngatang/60c2bdb54d156a41194446737ce03e2e?permalink_comment_id=3655412#gistcomment-3655412)

The issue was fixed by doing the following. 1. Click "Show Code" on the code cell where parameters (Bucket, Task, and Albert_Model) are filled in 2. If you've already run...

Closest I could get to was [here](https://github.com/tensorflow/tensorflow/blob/87462bfac761435a46641ff2f10ad0b6e5414a4b/tensorflow/python/estimator/estimator.py), but I can't quite figure out where `tensorflow_estimator` is.

I'm using Llama via HuggingFace. Is there a good way to make this edit through their modules at all? I tried doing ``` # this does not work torch.set_default_tensor_type(torch.cuda.HalfTensor) outputs...