3.01 GB
11 files
Updated 3 months ago
Name
Size
.gitattributes1.52 kB
xet
LICENSE.txt7.71 kB
xet
README.md1.51 kB
xet
USE_POLICY.md6.02 kB
xet
config.json877 Bytes
xet
eval.sh1.2 kB
xet
generation_config.json189 Bytes
xet
model.safetensors3 GB
xet
special_tokens_map.json325 Bytes
xet
tokenizer.json9.09 MB
xet
tokenizer_config.json54.6 kB
xet
README.md

🦙 Llama-3.2-1B-Instruct-abliterated

This is an uncensored version of Llama 3.2 1B 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:1b directly,

ollama run huihui_ai/llama3.2-abliterate:1b

Evaluations

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

Benchmark Llama-3.2-1B-Instruct Llama-3.2-1B-Instruct-abliterated
IF_Eval 58.50 56.88
MMLU Pro 16.35 14.35
TruthfulQA 43.08 38.96
BBH 33.75 31.83
GPQA 25.96 26.39
The script used for evaluation can be found inside this repository under /eval.sh, or click here
Total size
3.01 GB
Files
11
Last updated
Jun 27
Pre-warmed CDN
US EU US EU

Contributors