Abliterated version of Google's Gemma 2 9B
3,965 Pulls Updated 4 months ago
Updated 4 months ago
4 months ago
537424b6c203 · 6.6GB
model
archgemma2
·
parameters9.24B
·
quantizationQ5_K_M
6.6GB
params
{"stop":["\u003cstart_of_turn\u003e","\u003cend_of_turn\u003e"]}
65B
template
<start_of_turn>user
{{ if .System }}{{ .System }} {{ end }}{{ .Prompt }}<end_of_turn>
<start_of_turn
136B
license
Gemma Terms of Use
Last modified: February 21, 2024
By using, reproducing, modifying, distributin
8.4kB
Readme
Abliterated Gemma 2 9B
See on Huggingface
Abliterated version of Google’s Gemma 2 9B.
The abliteration script is based on code from the blog post and heavily uses TransformerLens. The only major difference from the code used for Llama is scaling the embedding layer back.