CoolFace
Modelpublic

DreadPoor/abliteration-OVA-8B-r128-LORA

sourceHugging Faceupdated 2y agoView on Hugging Face
1likes
Model Card

Untitled LoRA Model (1)

This is a LoRA extracted from a language model. It was extracted using mergekit.

LoRA Details

This LoRA adapter was extracted from grimjim/Llama-3-Instruct-abliteration-OVA-8B and uses NousResearch/Meta-Llama-3.1-8B-Instruct as a base.

Parameters

The following command was used to extract this LoRA adapter:

sh
mergekit-extract-lora grimjim/Llama-3-Instruct-abliteration-OVA-8B NousResearch/Meta-Llama-3.1-8B-Instruct OUTPUT_PATH --no-lazy-unpickle --skip-undecomposable --rank=128 --verbose