Hugging Face's logo

Spaces:
hf-accelerate
/
model-memory-usage
Running on CPU Upgrade

App Files Community
37
muellerzr HF staff commited on
Commit
2073499
·
1 Parent(s): a2fc477

emoji

Browse files
Files changed (1) hide show
  1. app.py +1 -1
app.py CHANGED
@@ -52,7 +52,7 @@ with gr.Blocks() as demo:
52
  """# Model Memory Calculator
53
 
54
  This tool will help you calculate how much vRAM is needed to train and perform big model inference
55
- on a model hosted on the :hugging_face: Hugging Face Hub. The minimum recommended vRAM needed for a model
56
  is denoted as the size of the "largest layer", and training of a model is roughly 4x its size (for Adam).
57
 
58
  Currently this tool supports all models hosted that use `transformers` and `timm`.
 
52
  """# Model Memory Calculator
53
 
54
  This tool will help you calculate how much vRAM is needed to train and perform big model inference
55
+ on a model hosted on the 🤗 Hugging Face Hub. The minimum recommended vRAM needed for a model
56
  is denoted as the size of the "largest layer", and training of a model is roughly 4x its size (for Adam).
57
 
58
  Currently this tool supports all models hosted that use `transformers` and `timm`.