Hugging Face's logo

jingyiZ00
/
R1-VL-2B

Image-Text-to-Text
Transformers
Safetensors
qwen2_vl
conversational
text-generation-inference
Model card Files Community

R1-VL-2B

R1-VL-2B is a reasoning model trained with step-wise group relative policy optimization (StepGRPO).

Paper: https://arxiv.org/pdf/2503.12937

Github: https://github.com/jingyi0000/R1-VL

Base model: https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct

Downloads last month
80
Safetensors
Model size
2.21B params
Tensor type
F32
·
Inference Providers NEW
Image-Text-to-Text
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for jingyiZ00/R1-VL-2B

Base model

Qwen/Qwen2-VL-2B
Finetuned
Qwen/Qwen2-VL-2B-Instruct
Finetuned
(178)
this model

Dataset used to train jingyiZ00/R1-VL-2B

Collection including jingyiZ00/R1-VL-2B