0gal1
/

R1-Fuzz-7B

Model card Files Files and versions

R1-Fuzz-7B

R1-Fuzz-7B is a model fine-tuned for the task of fuzzing input generation. It's trained based on Qwen2.5-7B-Instruct by GRPO.

Project code: https://github.com/HKU-System-Security-Lab/R1-Fuzz

Paper: https://arxiv.org/abs/2509.20384

Downloads last month: 24

Safetensors

Model size

8B params

Tensor type

BF16

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for 0gal1/R1-Fuzz-7B

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Finetuned

(2238)

this model

Quantizations

1 model