An REC ehanched Qwen 2.5VL 3B with VLM-R1 reinforcement learning.

cite: arxiv.org/abs/2504.07615

Downloads last month
924
Safetensors
Model size
3.75B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for omlab/Qwen2.5VL-3B-VLM-R1-REC-500steps

Finetuned
(115)
this model
Finetunes
1 model

Dataset used to train omlab/Qwen2.5VL-3B-VLM-R1-REC-500steps

Collection including omlab/Qwen2.5VL-3B-VLM-R1-REC-500steps