Hugging Face's logo

ZeroWw
/
Llama-3.2-3B-Instruct-abliterated-GGUF

Text Generation
GGUF
English
Inference Endpoints
conversational
Model card Files Community
Llama-3.2-3B-Instruct-abliterated-GGUF / Llama-3.2-3B-Instruct-abliterated /README.md
ZeroWw's picture
ZeroWw
Upload folder using huggingface_hub
6c799e2 verified
preview code
|
raw
history blame contribute delete
1.33 kB
metadata
library_name: transformers
license: llama3.2
base_model: meta-llama/Llama-3.2-3B-Instruct
tags:
  - abliterated
  - uncensored

🦙 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.

Evaluations

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