maximsemenov
/

tts-finetune

cross-attention

Model card Files Files and versions

model.py

Model Overview

A large-scale implementation of the perceiver architecture, built for contrastive tasks.

Architecture

Architecture: perceiver
Scale: large
Attention: flash
Fusion strategy: cross attention
Task head: contrastive
Activation: swish
Normalization: rmsnorm
Initialization: kaiming

Training

Optimizer: adam
LR scheduler: cosine

Files

model.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