Downloads · 30 days
12
32% of all-time downloads
RDA_llamagen
CSU-JPG/RDA_llamagen
RDA_llamagen is a machine learning model from CSU-JPG. 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 other.
This repository contains the Residual Decoder Adapter (RDA) / residual VQ weights for RDA tokenizer inference.
All-time downloads
38
Public
Repo size
778 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt778 MB · 100%
At a glance
- License
- other
- Access
- Public
- Created
- Jun 6, 2026
- Updated
- Jun 6, 2026
- SHA
- 2fbe69a0
Model card
From the Hugging Face model README
RDA LlamaGen Weights
This repository contains the Residual Decoder Adapter (RDA) / residual VQ weights for RDA tokenizer inference.
It does not include the base LlamaGen VQ checkpoint. Provide the base VQ checkpoint separately when loading the model.
Files
config.json
rda_model.pt
Loading
from tokenizer.tokenizer_image.rda_model import RDATokenizer
model = RDATokenizer.from_pretrained(
"neversa/RDA_llamagen",
vq_ckpt="/path/to/vq_ds16_t2i.pt",
).to("cuda")
outputs = model("/path/to/image.jpg")
outputs.prediction.save("prediction.png")
- License
- other
- Created
- Jun 6, 2026
- Updated
- Jun 6, 2026