Downloads · 30 days
0
Llama-3-Instruct-abliteration-LoRA-8B
grimjim/Llama-3-Instruct-abliteration-LoRA-8B
Llama-3-Instruct-abliteration-LoRA-8B is a machine learning model from grimjim. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as llama3.
This is a rank=32 LoRA extracted from a language model. It was extracted using mergekit.
Access
Public
Updated Sep 10, 2024
Repo size
176 MB
Likes
8
Public
Repo makeup
Click a slice to open those files.
.safetensors176 MB · 100%
At a glance
- Library
- transformers
- License
- llama3
- Access
- Public
- Created
- Jul 4, 2024
- Updated
- Sep 10, 2024
- SHA
- 454361d8
Base models
Model card
From the Hugging Face model README
Llama-3-Instruct-abliteration-LoRA-8B
This is a rank=32 LoRA extracted from a language model. It was extracted using mergekit.
This LoRA is derived from the refusal ablation vector also computed in Llama-3-Instruct-abliteration-OVA-8B, and is around 5 orders of magnitude smaller than full bf16 weights of the base model.
LoRA Details
This LoRA adapter was extracted from failspy/Meta-Llama-3-8B-Instruct-abliterated-v3 and uses meta-llama/Meta-Llama-3-8B-Instruct as a base.
Parameters
The following command was used to extract this LoRA adapter:
mergekit-extract-lora meta-llama/Meta-Llama-3-8B-Instruct failspy/Meta-Llama-3-8B-Instruct-abliterated-v3 OUTPUT_PATH --rank=32 --model_name=Llama-3-8B-Instruct-counter-refusal
- Library
- transformers
- License
- llama3
- Created
- Jul 4, 2024
- Updated
- Sep 10, 2024