Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models

motivation Our paper, code, data, models can be found at MIS.

Description

Qwen2-VL-7B-Instruct model fine-tuned on MIS training set.

MIRgae

mirage Here is example pipeline of MIS training set and MIRage safety CoT label construction.

You can fine-tune Qwen2-VL series using LlamaFactory.

Downloads last month
2
Safetensors
Model size
8.29B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and HF Inference API was unable to determine this model's library.

Model tree for Tuwhy/Qwen2-VL-7B-MIRage

Base model

Qwen/Qwen2-VL-7B
Finetuned
(142)
this model

Dataset used to train Tuwhy/Qwen2-VL-7B-MIRage