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.
Configuration
In addition to downloading the model, download the config file. This can be imported into LM Studio as a preset for simple use.
Some variations from the default system prompt have been tested and do affect how the model performs against the classifier.
Access
Access to this model is gated, make a request if you are interested.
- Downloads last month
- -
Hardware compatibility
Log In
to view the estimation
4-bit
6-bit
8-bit
16-bit
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support