New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Update default compute precision in readme #81

Open

Franck-Dernoncourt wants to merge 1 commit into huggingface:main from Franck-Dernoncourt:patch-1

Franck-Dernoncourt commented Jul 2, 2024

Since PR #58, float16 is the default compute precision in CLI

Note that float16 is the default compute precision only in the CLI, as in the code, default is still float32:

exporters/src/exporters/coreml/convert.py

Line 632 in 2f5ac17

quantize: str = "float32",

,

I think we need to be consistent.


          Update default compute precision in readme (since PR huggingface#58, …

68d86d5

…float16 is the default compute precision in CLI)

Note that `float16` is the default compute precision only in the CLI, as in the code, default is still `float32`:

https://github.com/huggingface/exporters/blob/2f5ac175a3bedb51fac28527afdff1371fa4eaed/src/exporters/coreml/convert.py#L632, 

I think we need to be consistent.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet