metadata

datasets:
  - SaisExperiments/Big-Alpaca-Uncensored
language:
  - en
base_model:
  - meta-llama/Llama-3.2-3B-Instruct

QuantFactory/Evil-Alpaca-3B-L3.2-GGUF

This is quantized version of SaisExperiments/Evil-Alpaca-3B-L3.2 created using llama.cpp

Original Model Card

This is an experimental? model I have trained over Llama-3.2-3B-Instruct.

It is compatible with both Llama3 & Alpaca prompt format.

So far it seems to be quite uncensored, it also has a tendency to call the user derogatory terms (whoops >:3)