Downloads · 30 days
0
model_076707635_perceiver_nano
mbertrand7905/model_076707635_perceiver_nano
model_076707635_perceiver_nano is a machine learning model from mbertrand7905. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as bsd-3-clause.
A nano-scale implementation of the perceiver architecture, built for multitask tasks.
Access
Public
Updated Aug 23, 2026
Repo size
—
Likes
0
Public
Repo makeup
Click a slice to open those files.
.py2.4 KB · 51%
At a glance
- License
- bsd-3-clause
- Access
- Public
- Created
- Aug 23, 2026
- Updated
- Aug 23, 2026
- SHA
- 6db2dad4
Model card
From the Hugging Face model README
model_076707635_perceiver_nano.py
Model Overview
A nano-scale implementation of the perceiver architecture, built for multitask tasks.
Architecture
- Architecture: perceiver
- Scale: nano
- Attention: sliding window
- Fusion strategy: cross attention
- Task head: multitask
- Activation: mish
- Normalization: groupnorm
- Initialization: kaiming
Training
- Optimizer: adam
- LR scheduler: polynomial
Files
model_076707635_perceiver_nano.py— main artifact of this repository
License
See the license field above.
- License
- bsd-3-clause
- Created
- Aug 23, 2026
- Updated
- Aug 23, 2026