Downloads · 30 days
19
22% of all-time downloads
ReToken-InternVL3.5-8B
AvaXiao/ReToken-InternVL3.5-8B
ReToken-InternVL3.5-8B is a image-text-to-text model from AvaXiao. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as mit.
This repository contains the model from the paper ReToken: One Token to Improve Vision-Language Models for Visual Retrieval.
All-time downloads
88
Public
Parameters
8.5B
17.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors17.1 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- License
- mit
- Model type
- internvl_chat
- Access
- Public
- Created
- Jun 11, 2026
- Updated
- Aug 1, 2026
- SHA
- 2b8ad0ff
Try a prompt
Model card
From the Hugging Face model README
ReToken: One Token to Improve Vision–Language Models for Visual Retrieval
This repository contains the model from the paper ReToken: One Token to Improve Vision-Language Models for Visual Retrieval.
ReToken is a single learnable embedding trained as an explicit retrieval target that selects a sparse set of query-relevant visual tokens from a pre-filled visual KV cache.
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- internvl_chat
- License
- mit
- Created
- Jun 11, 2026
- Updated
- Aug 1, 2026