Llama-3.2-3B-Instruct-abliterated

🦙 Llama-3.2-3B-Instruct-abliterated

This is an uncensored version of Llama 3.2 3B Instruct created with abliteration (see this article to know more about it).

Special thanks to @FailSpy for the original code and technique. Please follow him if you're interested in abliterated models.

ollama

You can use huihui_ai/llama3.2-abliterate:3b directly,

ollama run huihui_ai/llama3.2-abliterate

or create your own model using the following methods.

1. Download this model.

huggingface-cli download huihui-ai/Llama-3.2-3B-Instruct-abliterated --local-dir ./huihui-ai/Llama-3.2-3B-Instruct-abliterated

1. Get Llama-3.2-3B-Instruct model for reference.

ollama pull llama3.2

1. Export Llama-3.2-3B-Instruct model parameters.

ollama show llama3.2 --modelfile > Modelfile

1. Modify Modelfile, Remove all comment lines (indicated by #) before the "FROM" keyword. Replace the "FROM" with the following content.

FROM huihui-ai/Llama-3.2-3B-Instruct-abliterated

1. Use ollama create to then create the quantized model.

ollama create --quantize q4_K_M -f Modelfile Llama-3.2-3B-Instruct-abliterated-q4_K_M

1. Run model

ollama run Llama-3.2-3B-Instruct-abliterated-q4_K_M

The running architecture is llama.

Evaluations

The following data has been re-evaluated and calculated as the average for each test.

The script used for evaluation can be found inside this repository under /eval.sh, or click here