Kangxi Wu

You can try to update "scikit-learn", then install llmdet.

> @cansee5 I think you have to change "sklearn" to "scikit-learn" in the setup.py file Sorry, I made a mistake, I have updated setup.py file, thank you very much for...

If you only need to use the detection feature of "llmdet" and don't need to worry about the dataset issue, you can simply follow the methods described in the README.md...

Thank you for your interest in our work. Can you provide more detailed information? Like your code and what‘s wrong with it to help me understand what you’re doing so...

The testing files will be uploaded to HuggingFace, and you can download them from the following URL: https://huggingface.co/datasets/TryMore/n_grams_probability.

Regarding closed-source models, we will provide an extended interface for LLMDet dictionary construction. We hope that model owners can assist us in building the dictionary, while this interface will ensure...

If you want to expand the dictionary to adapt to the new model, first you need to use the new model to generate text. My suggestion is preferably more than...

Yes, you can replace [decapoda-research/llama-7b-hf](https://huggingface.co/decapoda-research/llama-7b-hf) with [baffo32/decapoda-research-llama-7B-hf](https://huggingface.co/baffo32/decapoda-research-llama-7B-hf).

If you want to extend LLMDet to a new model, you can do so according to the logic in the run_main.py (https://github.com/TrustedLLM/LLMDet/blob/main/main-experiment/run_main.py), we only planned the extension functionality in the...