Hugging Face's logo

Spaces:
jesseplusplus
/
easy-translate
Running

App Files Community
Iker commited on
Commit
f72813d
•
1 Parent(s): a571fee

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -24,7 +24,7 @@ Easy-Translate is built on top of 🤗HuggingFace's [Transformers](https://huggi
24
  We currently support:
25
 
26
  - CPU / GPU / multi-GPU / TPU acceleration
27
- - BF16 / FP16 / FB32 precision.
28
  - Automatic batch size finder: Forget CUDA OOM errors. Set an initial batch size, if it doesn't fit, we will automatically adjust it.
29
  - Sharded Data Parallel to load huge models sharded on multiple GPUs (See: <https://huggingface.co/docs/accelerate/fsdp>).
30
 
 
24
  We currently support:
25
 
26
  - CPU / GPU / multi-GPU / TPU acceleration
27
+ - BF16 / FP16 / FP32 precision.
28
  - Automatic batch size finder: Forget CUDA OOM errors. Set an initial batch size, if it doesn't fit, we will automatically adjust it.
29
  - Sharded Data Parallel to load huge models sharded on multiple GPUs (See: <https://huggingface.co/docs/accelerate/fsdp>).
30