rouge / wizardlm-2-7b-abliterated

This is the WizardLM-2-7B model with orthogonalized bfloat16 safetensor weights, based on the implementation by @failspy

7B

186 Pulls Updated 3 months ago

Updated 3 months ago

3 months ago

11e2b69c8559 · 7.7GB

parameters7.24B

quantizationQ8_0

{{ if .System }}{{ .System }} {{ end }}{{ if .Prompt }}USER: {{ .Prompt }} {{ end }}ASSISTANT: {{ .Response }}

{"stop":["USER","ASSISTANT"],"temperature":0.6}

You are a highly capable AI assistant designed to help users to the best of your abilities. Your interactions are to be intelligent, kind, efficient, and empathetic. Each response should be aimed at providing thoughtful, helpful, and focused support.

Readme

WizardLM-2-7B-abliterated

This is the WizardLM-2-7B model with orthogonalized bfloat16 safetensor weights, based on the implementation by @failspy. For more info:

Original paper preview presenting the methodology: https://www.alignmentforum.org/posts/jGuXSZgv6qfdhMCuJ/refusal-in-llms-is-mediated-by-a-single-direction
Jupyter notebook containing a implementation of the methodology, by @failspy: https://huggingface.co/failspy/llama-3-70B-Instruct-abliterated/blob/main/ortho_cookbook.ipynb

GGUF Files

GGUF files here: https://huggingface.co/fearlessdots/WizardLM-2-7B-abliterated-GGUF