With the adapter from Anjir, you can turn any LLaMA-3 8B model into some random thug.
Edit: Works better with abliterated model.
64 RANK VERSION
This is a LoRA extracted from a language model. It was extracted using mergekit.
LoRA Details
This LoRA adapter was extracted from Hastagaras/Anjir-8B-L3 and uses meta-llama/Meta-Llama-3-8B as a base.
Parameters
The following command was used to extract this LoRA adapter:
mergekit-extract-lora meta-llama/Meta-Llama-3-8B Hastagaras/Anjir-8B-L3 OUTPUT_PATH --no-lazy-unpickle --rank=64