Downloads · 30 days
146
11% of all-time downloads
RichardErkhov/Edgerunners_-_meta-llama-3-8b-instruct-hf-ortho-baukit-2fail-128total-gguf
Edgerunners_-_meta-llama-3-8b-instruct-hf-ortho-baukit-2fail-128total-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
146
11% of all-time downloads
All-time downloads
1.3K
Public
Repo size
92.9 GB
Likes
0
Public
Click a slice to open those files.
.gguf108 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
meta-llama-3-8b-instruct-hf-ortho-baukit-2fail-128total - GGUF
test results: works extremely well if system prompt and card aren't empty.
this version had only 2 refusals out of 128 ortho-tests.
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