Skip to main content

Griffin - Pytorch

Project description

Multi-Modality

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


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-0.0.3.tar.gz (4.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

griffin_torch-0.0.3-py3-none-any.whl (4.9 kB view details)

Uploaded Python 3

File details

Details for the file griffin_torch-0.0.3.tar.gz.

File metadata

  • Download URL: griffin_torch-0.0.3.tar.gz
  • Upload date:
  • Size: 4.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.3.2 CPython/3.11.0 Darwin/23.3.0

File hashes

Hashes for griffin_torch-0.0.3.tar.gz
Algorithm Hash digest
SHA256 61bf1baa51ca906aa0b2785bbdb3e466fae00e2787fd14a32ba182463df6c37d
MD5 2961704eb19a588edc12be6591983dcb
BLAKE2b-256 88e64c282c5d9bd2dab6e762a2fe10e21655bedaec7288d58ca6b8f0888ac52b

See more details on using hashes here.

File details

Details for the file griffin_torch-0.0.3-py3-none-any.whl.

File metadata

  • Download URL: griffin_torch-0.0.3-py3-none-any.whl
  • Upload date:
  • Size: 4.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.3.2 CPython/3.11.0 Darwin/23.3.0

File hashes

Hashes for griffin_torch-0.0.3-py3-none-any.whl
Algorithm Hash digest
SHA256 dc9a42a5bae2b77ef661780a1ca0f5dbd1cde93a3cac668aad8f9dd5388e8d4a
MD5 9384d530d99326e3aee800e0a4c4faff
BLAKE2b-256 2b56843d2fb58540867cbccff543580d6fd8baa9c0259af015e3b770ecb6ebb8

See more details on using hashes here.

Supported by

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