QuixiAI/Llama-3-8B-Instruct-abliterated-v2
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
fs
2024-05-09 02:28:55 +00:00
committed by system
parent 24d0a3a7ca
commit 4c4c3ccd25
1 changed files with 18 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
README.md
View File

@@ -1,23 +1,30 @@
---
library_name: transformers
tags: []
license: llama3
---
# Llama-3-8B-Instruct-abliterated-v2 Model Card
This is meta-llama/Llama-3-8B-Instruct with orthogonalized bfloat16 safetensor weights, generated with the methodology that was described in the preview paper/blog post: '[Refusal in LLMs is mediated by a single direction](https://www.alignmentforum.org/posts/jGuXSZgv6qfdhMCuJ/refusal-in-llms-is-mediated-by-a-single-direction)' which I encourage you to read to understand more.
# Model Card for Llama-3-8B-Instruct-abliterated-v2
TL;DR: this model has had certain weights manipulated to "inhibit" the model's ability to express refusal. It is not in anyway _guaranteed_ that it won't refuse you, understand your request, it may still lecture you about ethics/safety, etc. It is tuned in all other respects the same as the original 8B instruct model was, just with the strongest refusal direction orthogonalized out.
## Overview
This model card describes the Llama-3-8B-Instruct-abliterated-v2 model, which is an orthogonalized version of the meta-llama/Llama-3-8B-Instruct model, and an improvement upon the previous generation Llama-3-8B-Instruct-abliterated. This variant has had certain weights manipulated to inhibit the model's ability to express refusal.
[GGUF Quants Here](https://huggingface.co/failspy/Llama-3-8B-Instruct-abliterated-v2-GGUF)
[Join the Cognitive Computations Discord!](https://discord.gg/cognitivecomputations)
## V2 statement
## Details
This model was trained with more data to better pinpoint the "refusal direction".
* The model was trained with more data to better pinpoint the "refusal direction".
* This model is MUCH better at directly and succinctly answering requests without producing even so much as disclaimers.
This model is MUCH better at directly and succinctly answering requests without producing even so much as disclaimers.
## Methodology
## Quirkiness awareness notice
The methodology used to generate this model is described in the preview paper/blog post: '[Refusal in LLMs is mediated by a single direction](https://www.alignmentforum.org/posts/jGuXSZgv6qfdhMCuJ/refusal-in-llms-is-mediated-by-a-single-direction)'
This model may come with interesting quirks, as I obviously haven't extensively tested it, and the methodology being so new. I encourage you to play with the model, and post any quirks you notice in the community tab, as that'll help us further understand what this orthogonalization has in the way of side effects. The code I used to generate it (and my published 'Kappa-3' model which is just Phi-3 with the same methodology applied) is available in the Python notebook [ortho_cookbook.ipynb](https://huggingface.co/failspy/llama-3-70B-Instruct-abliterated/blob/main/ortho_cookbook.ipynb).
## Quirks and Side Effects
This model may come with interesting quirks, as the methodology is still new and untested. The code used to generate the model is available in the Python notebook [ortho_cookbook.ipynb](https://huggingface.co/failspy/llama-3-70B-Instruct-abliterated/blob/main/ortho_cookbook.ipynb).
Please note that the model may still refuse to answer certain requests, even after the weights have been manipulated to inhibit refusal.
If you manage to develop further improvements, please share! This is really the most primitive way to use ablation, but there are other possibilities that I believe are as-yet unexplored.
## Availability
## How to Use
This model is available for use in the Transformers library.
GGUF Quants are available [here](https://huggingface.co/failspy/Llama-3-8B-Instruct-abliterated-v2-GGUF).