Gated Slot Attention - Pytorch
Project description
Gated Slot Attention
Usage
import torch
from gated_slot_attention.model import GSATransformer
model = GSATransformer(
dim=512,
heads=8,
m=64,
tau=0.1,
depth=1,
vocab_size=10000,
max_seq_len=1024,
)
x = torch.randint(0, 10000, (1, 1024))
out = model(x)
print(out.shape)
License
MIT
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
Built Distribution
Close
Hashes for gated_slot_attention-0.0.1.tar.gz
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | be2758fd001a81b1ff1f3ababc62e09231d826fea387d43bbd3a7eecc9f206b6 |
|
| MD5 | 99688abe7d5abd92d8962ab075e9675f |
|
| BLAKE2b-256 | 6d2204728f8c974bf56e6c56dc7cf58368a6a7613f2e25e3d2605e1b57ca816e |
Close
Hashes for gated_slot_attention-0.0.1-py3-none-any.whl
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 5afce2322c21ceba30ccf73ee08c144fb7e3336f475881f098378a3bd37324c8 |
|
| MD5 | c190723dc8021a233feeea9378e04f9a |
|
| BLAKE2b-256 | b8c257db15f9525977620c41875673aeb7a302638f5b3844ac39185f39023e30 |
