48 2 months ago

This is an essay writing model extremely effective at evading the ZeroGPT classifier. Performance is not guaranteed on other AI detection tools. This model is for research only, please do not use it for malicious purposes or to cheat on your homework.

tools thinking

2 months ago

346314456a2d · 1.8GB ·

qwen3
·
1.72B
·
Q8_0
{{- $lastUserIdx := -1 -}} {{- range $idx, $msg := .Messages -}} {{- if eq $msg.Role "user" }}{{ $la
You are an expert academic writer. Your task is to write a complete, well-researched, and impeccably
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International Creative Commons Corporat
{ "num_ctx": 8192, "repeat_penalty": 1.05, "stop": [ "<|im_start|>", "<|

Readme

Model Card for Trojan-1-Qwen3-1.7B

Model Details

This model was fine tuned with GRPO using the ZeroGPT as the reward function, making it extremely effective at evading the ZeroGPT and GPTZero classifiers.

Model performance is not guaranteed on other AI detection tools.

The model on Ollama is quantized to Q8_0.

Installation

Run this command in your terminal.

ollama run Beanie/Trojan-1-Preview-Qwen3-1.7B

Some variations from the default system prompt have been tested and do affect how the model performs against the classifier.