English
Autoregressive
Tokenizer
nielsr HF Staff commited on
Commit
9ab1565
·
verified ·
1 Parent(s): 280314d

Add image-to-image pipeline tag

Browse files

This PR improves the model card by adding the `image-to-image` pipeline tag.

Files changed (1) hide show
  1. README.md +3 -2
README.md CHANGED
@@ -1,10 +1,11 @@
1
  ---
2
- license: apache-2.0
3
  language:
4
  - en
 
5
  tags:
6
  - Autoregressive
7
  - Tokenizer
 
8
  ---
9
 
10
  ## Taming Scalable Visual Tokenizer for Autoregressive Image Generation
@@ -15,4 +16,4 @@ Paper: https://arxiv.org/abs/2412.02692
15
  This repo is used for hosting IBQ’s checkpoints.
16
 
17
  ## Introduction
18
- 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.
 
1
  ---
 
2
  language:
3
  - en
4
+ license: apache-2.0
5
  tags:
6
  - Autoregressive
7
  - Tokenizer
8
+ pipeline_tag: image-to-image
9
  ---
10
 
11
  ## Taming Scalable Visual Tokenizer for Autoregressive Image Generation
 
16
  This repo is used for hosting IBQ’s checkpoints.
17
 
18
  ## Introduction
19
+ 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.