jaahas / gemma-2-9b-it-abliterated

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

parameters9.24B

quantizationQ5_K_M

{"stop":["\u003cstart_of_turn\u003e","\u003cend_of_turn\u003e"]}

<start_of_turn>user {{ if .System }}{{ .System }} {{ end }}{{ .Prompt }}<end_of_turn> <start_of_turn

Gemma Terms of Use Last modified: February 21, 2024 By using, reproducing, modifying, distributin

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.