You can deploy this model and start earning money today!

BlackHillsInformationSecurity/
Llama-3.2-3B-Instruct-abliterated

Name: Llama-3.2-3B-Instruct-abliterated
Availability: InStock

Views

No views yet

🦙 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 run huihui_ai/llama3.2-abliterate

or create your own model using the following methods.

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

ollama pull llama3.2

ollama show llama3.2 --modelfile > Modelfile

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

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

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

The running architecture is llama.

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

Benchmark	Llama-3.2-3B-Instruct	Llama-3.2-3B-Instruct-abliterated
IF_Eval	76.55	76.76
MMLU Pro	27.88	28.00
TruthfulQA	50.55	50.73
BBH	41.81	41.86
GPQA	28.39	28.41

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