Downloads · 30 days
12
14% of all-time downloads
IBQ-AR-L
TencentARC/IBQ-AR-L
IBQ-AR-L is a machine learning model from TencentARC. 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 apache-2.0.
Code: https://github.com/TencentARC/SEED-Voken
All-time downloads
87
Public
Repo size
3 GB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.ckpt3 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Dec 4, 2024
- Updated
- Dec 30, 2024
- SHA
- 9720f89a
Model card
From the Hugging Face model README
Taming Scalable Visual Tokenizer for Autoregressive Image Generation
Code: https://github.com/TencentARC/SEED-Voken
Paper: https://arxiv.org/abs/2412.02692
This repo is used for hosting IBQ’s checkpoints.
Introduction
We propose Index Backpropagation Quantization (IBQ), a new vector quantization method for the joint optimization of all codebook embeddings and the visual encoder, ensuring the consistent latent space. IBQ enables scalable training of visual tokenizers and, for the first time, achieves a large-scale codebook (2^18) with high dimension (256) and high utilization.
- License
- apache-2.0
- Languages
- en
- Created
- Dec 4, 2024
- Updated
- Dec 30, 2024