Beckernoah
/

unet-qa

cross-attention

Model card Files Files and versions

finetune.py

Model Overview

A giant-scale implementation of the hybrid architecture, built for matching tasks.

Architecture

Architecture: hybrid
Scale: giant
Attention: flash
Fusion strategy: cross attention
Task head: matching
Activation: approx gelu
Normalization: instancenorm
Initialization: trunc normal

Training

Optimizer: rmsprop
LR scheduler: cosine

Files

finetune.py — main artifact of this repository

License

See the license field above.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support