Hugging Face's logo

sfeucht
/
footprints

Model card Files Community
sfeucht commited on
Commit
088f361
·
verified ·
1 Parent(s): 660679f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -27,6 +27,6 @@ checkpoint_path = hf_hub_download(
27
 
28
  # model_size is 4096 for both models.
29
  # vocab_size is 32000 for Llama-2-7b and 128256 for Llama-3-8b
30
- probe = LinearModel(4096, 32000)
31
- probe.load_state_dict(torch.load(checkpoint_path, map_location=torch.device('cpu')))
32
  ```
 
27
 
28
  # model_size is 4096 for both models.
29
  # vocab_size is 32000 for Llama-2-7b and 128256 for Llama-3-8b
30
+ probe = LinearModel(4096, 32000).cuda()
31
+ probe.load_state_dict(torch.load(checkpoint_path))
32
  ```