omlab
/

VLM-R1-Qwen2.5VL-3B-Math-0305

Visual Question Answering

Model card Files Files and versions

A Math ehanched Qwen 2.5VL 3B with VLM-R1 reinforcement learning.

cite: arxiv.org/abs/2504.07615

Downloads last month: 62

Safetensors

Model size

4B params

Tensor type

BF16

·

Model tree for omlab/VLM-R1-Qwen2.5VL-3B-Math-0305

Base model

Qwen/Qwen2.5-VL-3B-Instruct

Finetuned

(616)

this model

Quantizations

1 model

Datasets used to train omlab/VLM-R1-Qwen2.5VL-3B-Math-0305

Collection including omlab/VLM-R1-Qwen2.5VL-3B-Math-0305

VLM-R1-models

A collection of VLM-R1 Models • 7 items • Updated Jul 11, 2025 • 9