Mihai 0bc6779361 Disable autocast for cpu to fix error. Remove unused precision arg. (#518) ...

When running on just cpu (intel), a call to torch.layer_norm would error with RuntimeError: expected scalar type BFloat16 but found Float
Fix buggy device handling in model.py.
Tested with scripts/dream.py --full_precision on just cpu on intel laptop. Works but slow at ~10s/it.

2022-09-12 16:55:21 -04:00

..

__init__.py

add code

2021-12-21 03:23:41 +01:00

model.py

Disable autocast for cpu to fix error. Remove unused precision arg. (#518)

2022-09-12 16:55:21 -04:00

openaimodel.py

prettified all the code using "blue" at the urging of @tildebyte

2022-08-26 03:15:42 -04:00

util.py

work around unexplained crash when timesteps=1000 (#440)

2022-09-08 20:41:37 -04:00