Downloads · 30 days
0
llama2.c_ghostmax
joey00072/llama2.c_ghostmax
llama2.c_ghostmax is a machine learning model from joey00072. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
ghostmax/softmax1 trained on tinystories for 500M tokens.
Access
Public
Updated Aug 25, 2023
Repo size
1.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt1 GB · 75%
At a glance
- License
- mit
- Access
- Public
- Created
- Aug 25, 2023
- Updated
- Aug 25, 2023
- SHA
- 24920406
Model card
From the Hugging Face model README
ghostmax/softmax1 trained on tinystories for 500M tokens.
ckpt will be out_* files trained 2 models 1 with regular softmax
REPO: https://github.com/joey00072/llama2.c/tree/ghostmax
softmax: https://wandb.ai/shubhamchoudhari00072/ghostmax/reports/loss-val-23-08-25-21-48-58---Vmlldzo1MjM0MjUw <br> ghostmax: https://wandb.ai/shubhamchoudhari00072/ghostmax/reports/loss-val-23-08-25-21-50-15---Vmlldzo1MjM0MjYw <br> <br>
def softmax(x, dim=None):
e_x = torch.exp(x - torch.max(x, dim=dim, keepdim=True)[0])
return e_x / e_x.sum(dim=dim, keepdim=True)
def ghostmax(x, dim=None):
e_x = torch.exp(x - torch.max(x, dim=dim, keepdim=True)[0])
return e_x / (1+e_x.sum(dim=dim, keepdim=True) )
- License
- mit
- Created
- Aug 25, 2023
- Updated
- Aug 25, 2023