Downloads · 30 days
18
15% of all-time downloads
TencentARC/IBQ-Tokenizer-8192
IBQ-Tokenizer-8192 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
Downloads · 30 days
18
15% of all-time downloads
All-time downloads
118
Public
Repo size
871 MB
Likes
1
Public
Click a slice to open those files.
.ckpt871 MB · 100%
From the Hugging Face model README
Code: https://github.com/TencentARC/SEED-Voken
Paper: https://arxiv.org/abs/2412.02692
This repo is used for hosting IBQ’s checkpoints.
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.