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.
Runs of TencentARC IBQ-AR-XXL on huggingface.co
9
Total runs
0
24-hour runs
0
3-day runs
-1
7-day runs
3
30-day runs
More Information About IBQ-AR-XXL huggingface.co Model
IBQ-AR-XXL huggingface.co is an AI model on huggingface.co that provides IBQ-AR-XXL's model effect (), which can be used instantly with this TencentARC IBQ-AR-XXL model. huggingface.co supports a free trial of the IBQ-AR-XXL model, and also provides paid use of the IBQ-AR-XXL. Support call IBQ-AR-XXL model through api, including Node.js, Python, http.
IBQ-AR-XXL huggingface.co is an online trial and call api platform, which integrates IBQ-AR-XXL's modeling effects, including api services, and provides a free online trial of IBQ-AR-XXL, you can try IBQ-AR-XXL online for free by clicking the link below.
TencentARC IBQ-AR-XXL online free url in huggingface.co:
IBQ-AR-XXL is an open source model from GitHub that offers a free installation service, and any user can find IBQ-AR-XXL on GitHub to install. At the same time, huggingface.co provides the effect of IBQ-AR-XXL install, users can directly use IBQ-AR-XXL installed effect in huggingface.co for debugging and trial. It also supports api for free installation.