Now with 100% more alignment!
41 Pulls Updated 4 months ago
Updated 4 months ago
4 months ago
77b95f23e5df · 3.4GB
model
archphi3
·
parameters3.82B
·
quantizationQ6_K
3.4GB
params
{"stop":["\u003c|end|\u003e","\u003c|user|\u003e","\u003c|assistant|\u003e"]}
78B
template
{{ if .System }}<|system|>
{{ .System }}<|end|>
{{ end }}{{ if .Prompt }}<|user|>
{{ .Prompt }}<|end
148B
license
Microsoft.
Copyright (c) Microsoft Corporation.
MIT License
Permission is hereby granted, free of
1.1kB
Readme
See on Huggingface
This is microsoft/Phi-3-mini-128k-instruct with orthogonalized bfloat16 safetensor weights, generated with a refined methodology based on that which was described in the preview paper/blog post: ‘Refusal in LLMs is mediated by a single direction’ which I encourage you to read to understand more.