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)
- Downloads last month
- 34
Model tree for SaisExperiments/Evil-Alpaca-3B-L3.2
Base model
meta-llama/Llama-3.2-3B-Instruct