Update README.md
#5
by
ybelkada
- opened
Add explicit warning message regarding float16
cc
@osanseviero
@ArthurZ
- note that this problem occurs only for the xxl model, generations with float16 & int8 works perfectly with the other models
ybelkada
changed pull request status to
closed
Closing as fixed, see https://github.com/huggingface/transformers/pull/20760