Fix code typo in code examples
#6
by
kubistmi
- opened
Hello 👋
Based on this PR for 2.2B version, this is the same change just for a different model (I will open one more for 500M 😉).
I have included param dtype=torch.bfloat16 when moving the processed inputs to CUDA (this is included in some examples, but not all).
This should avoid mismatched tensor types between model weights and inputs.
Cheers,
Michal
thank you
mfarre
changed pull request status to
merged