tokenizer-practice / README.md
danielmdm's picture
Upload 2 files
10e2d16 verified
|
Raw
History Blame Contribute Delete
710 Bytes
metadata
license: apache-2.0
tags:
  - batchnorm
  - blip
  - flash
  - gelu
  - generation
  - large
  - lion
  - orthogonal
  - polynomial
  - tucker

inference.py

Model Overview

A large-scale implementation of the blip architecture, built for generation tasks.

Architecture

  • Architecture: blip
  • Scale: large
  • Attention: flash
  • Fusion strategy: tucker
  • Task head: generation
  • Activation: gelu
  • Normalization: batchnorm
  • Initialization: orthogonal

Training

  • Optimizer: lion
  • LR scheduler: polynomial

Files

  • inference.py — main artifact of this repository

License

See the license field above.