Skip to main content

mmca-mgqa - Pytorch

Project description

Multi-Modality

Multi-Modal Casual Multi-Grouped Query Attention

Experiments around using Multi-Modal Casual Attention with Multi-Grouped Query Attention

Appreciation

  • Lucidrains
  • Agorians

Install

pip install mmmgqa

Usage

import torch 
from mmca_mgqa.attention import SimpleMMCA

# Define the dimensions
dim = 512
head = 8
seq_len = 10
batch_size = 32

#attn
attn = SimpleMMCA(dim=dim, heads=head)

#random tokens
v = torch.randn(batch_size, seq_len, dim)
t = torch.randn(batch_size, seq_len, dim)

#pass the tokens throught attn
tokens = attn(v, t)

print(tokens)

Architecture

Todo

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mmmgqa-0.0.2.tar.gz (3.0 kB view details)

Uploaded Source

Built Distribution

mmmgqa-0.0.2-py3-none-any.whl (3.0 kB view details)

Uploaded Python 3

File details

Details for the file mmmgqa-0.0.2.tar.gz.

File metadata

  • Download URL: mmmgqa-0.0.2.tar.gz
  • Upload date:
  • Size: 3.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.3.2 CPython/3.11.0 Darwin/22.4.0

File hashes

Hashes for mmmgqa-0.0.2.tar.gz
Algorithm Hash digest
SHA256 0ab9320fe3693b5590a560966c6460c96d36748e5e3bab8d3ca3fa69581ffcc0
MD5 620af15dd76899d136479189bb29f375
BLAKE2b-256 e28f6a39928e215f056514b984d4a559a194e0504a9782205a67f0cd1b319d6a

See more details on using hashes here.

File details

Details for the file mmmgqa-0.0.2-py3-none-any.whl.

File metadata

  • Download URL: mmmgqa-0.0.2-py3-none-any.whl
  • Upload date:
  • Size: 3.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.3.2 CPython/3.11.0 Darwin/22.4.0

File hashes

Hashes for mmmgqa-0.0.2-py3-none-any.whl
Algorithm Hash digest
SHA256 838f2005dfd24f9357024b63c2d405490929ca23c216398076cf54db4b882769
MD5 7f02092a199aec00f4baeacb0e76bf21
BLAKE2b-256 3f867d45f22fb76b40649a22ddd8c0ac322cb8f821a2f17fd0670a93947e67f5

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page