Downloads · 30 days
1
0% of all-time downloads
lucyknada/Edgerunners_meta-llama-3-8b-instruct-hf-ortho-baukit-34fail-3000total-bf16-GGUF
Edgerunners_meta-llama-3-8b-instruct-hf-ortho-baukit-34fail-3000total-bf16-GGUF is a machine learning model from lucyknada. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as cc-by-nc-4.0.
test results: needs testing compared to previous 33/3000 but this time it's in bf16
Downloads · 30 days
1
0% of all-time downloads
All-time downloads
1.7K
Public
Repo size
21.3 GB
Likes
0
Public
Click a slice to open those files.
.gguf21.3 GB · 100%
From the Hugging Face model README
test results: needs testing compared to previous 33/3000 but this time it's in bf16
this version had only 34 refusals out of 3000 ortho-tests, in-line with the others in terms of refusals.
wassname (updated baukit) implementation of the paper: https://www.alignmentforum.org/posts/jGuXSZgv6qfdhMCuJ/refusal-in-llms-is-mediated-by-a-single-direction applied to llama3 8b instruct