Fix code typo in code examples
#10
by
kubistmi
- opened
Hello 👋
Based on this PR for 2.2B version and this for 256M version.
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.
Sorry for spreading this over 3 PRs, I am not sure if there's a better way for such change🙂
Cheers,
Michal
Thank you!
pcuenq
changed pull request status to
merged