Hugging Face's logo

huihui-ai
/
Meta-Llama-3.1-8B-Instruct-abliterated

Text Generation
Transformers
Safetensors
llama
abliterated
uncensored
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
Meta-Llama-3.1-8B-Instruct-abliterated / README.md
huihui-ai's picture
huihui-ai
Update README.md
15f6d37 verified
preview code
|
raw
history blame
1.39 kB
metadata
library_name: transformers
license: llama3.1
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
tags:
  - abliterated
  - uncensored

🦙 Meta-Llama-3.1-8B-Instruct-abliterated

This is an uncensored version of Llama 3.1 8B 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-3.1-8b-Instruct Meta-Llama-3.1-8B-Instruct-abliterated
IF_Eval 80.0 78.98
MMLU Pro 36.34 35.91
TruthfulQA 52.98 55.42
BBH 48.72 47.0
GPQA 33.55 33.93

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