Griffin - Pytorch
Project description
Griffin
install
$ pip install griffin-torch
usage
import torch
from griffin_torch.main import Griffin
# Forward pass
x = torch.randint(0, 100, (1, 10))
# Model
model = Griffin(
dim = 512, # Dimension of the model
num_tokens = 100, # Number of tokens in the input
seq_len = 10, # Length of the input sequence
depth = 8, # Number of transformer blocks
mlp_mult = 4, # Multiplier for the hidden dimension in the MLPs
dropout = 0.1, # Dropout rate
)
# Forward pass
y = model(x)
print(y)
License
MIT
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
griffin_torch-0.0.2.tar.gz
(4.9 kB
view hashes)
Built Distribution
Close
Hashes for griffin_torch-0.0.2-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 528efb1f25ae6eb327e1f27c3ba39d7b8643a330df0220a89019bb6c158e2f0d |
|
MD5 | e5d9e25252b9c40b2f758b805ca8fb9f |
|
BLAKE2b-256 | fb9ea1ac10c0dcb7ff83689928d39b35baf9019a0f91cdce005919e598318db8 |