MIRage
Collection
Official model collection of paper: Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models
•
2 items
•
Updated
•
1
Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models
Our paper, code, data, models can be found at MIS.
Description
Qwen2-VL-7B-Instruct model fine-tuned on MIS training set.
MIRgae
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
- 38
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no library tag.