How to add local model?

[Pankaj Rawat]

I run llama13b via vllm on docker and access it with http://localhost:5555:v1
and how can I test on this

[jonathan | ヨナタン]

currently there is no direct way to add local models via Docker. But you can modify framework/llm.py and extend the LLM class to suit your needs for other custom local models.
The LLaMA2-13b model however is also supported by my framework directly by using the --llm_type llama2-13b argument when running the attacks.