Downloads · 30 days
10
24% of all-time downloads
Qwen3-VL-4B-Instruct-Action-V2
RBabakyan/Qwen3-VL-4B-Instruct-Action-V2
Qwen3-VL-4B-Instruct-Action-V2 is a image-text-to-text model from RBabakyan. 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.
This repository contains a Qwen base checkpoint with an extended robotics action tokenizer for GreenVLA and VLA initialization.
All-time downloads
41
Public
Parameters
4.4B
8.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors8.9 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- Model type
- qwen3_vl
- Access
- Public
- Created
- Jul 8, 2026
- Updated
- Jul 8, 2026
- SHA
- 26fe1992
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3-VL-4B-Instruct-Action-V2
This repository contains a Qwen base checkpoint with an extended robotics action tokenizer for GreenVLA and VLA initialization.
It is intended to be used as the base vision-language model checkpoint before loading task-specific robot policy weights.
Base Model
- Base model: Qwen/Qwen3-VL-4B-Instruct
- Target repository: RBabakyan/Qwen3-VL-4B-Instruct-Action-V2
Notes
The tokenizer includes additional action tokens required by the downstream robotics policy stack. Model files are provided in the standard Transformers format.
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- qwen3_vl
- Created
- Jul 8, 2026
- Updated
- Jul 8, 2026