Attention + Convolution transformer
This is an experimental architecture leveraging convolution blocks with attention blocks to model both the short and long range dynamics of the input tokens. The flow is the following: x -> convolution block -> attn -> FFN
Install
``
Usage
import torch
from attnconv.main import ATCTransformer
model = ATCTransformer(
dim=512,
depth=6,
num_tokens=20000,
dim_head=64,
heads=8,
ff_mult=4,
)
x = torch.randint(0, 20000, (1, 512))
logits = model(x) # (1, 1024, 20000)
print(logits)
License
MIT
1 maintainer
Metadata
1 maintainer
Release files for atc-torch 0.0.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| atc_torch-0.0.1.tar.gz | 5.0 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| atc_torch-0.0.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 9.9 kB
Release files / atc_torch-0.0.1.tar.gz
| Download URL | atc_torch-0.0.1.tar.gz |
|---|---|
| Size | 5.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
ecffece868b307a51e686f2550468435b5acb9df565097164e937cf83ea63ca7
|
|
BLAKE2b-256 checksum How to use checksums |
fd1773bfe8b4ec8700b2e2d98c435a33db52bc20d22341590469d80fa9c75de1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.3.2 CPython/3.11.0 Darwin/22.4.0
|
Release files / atc_torch-0.0.1-py3-none-any.whl
| Download URL | atc_torch-0.0.1-py3-none-any.whl |
|---|---|
| Size | 4.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
b84682bae3c6a32da53b041c12f2d976d1f33e662a5b9c412357df257ff3a318
|
|
BLAKE2b-256 checksum How to use checksums |
0119e9c5d11197e894623d62ebfb93232e5d08e77ca6a93d12bb5a95adf179c1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.3.2 CPython/3.11.0 Darwin/22.4.0
|
