huihui_ai/aya-expanse-abliterated:8b-q8_0

huihui_ai/aya-expanse-abliterated

Cohere For AI's language models trained to perform well across 23 different languages.

tools 8b 32b

57 Pulls Updated 5 days ago

Updated 6 days ago

6 days ago

7ff8c4d6e0cc · 8.5GB

parameters8.03B

quantizationQ8_0

{ "stop": [ "<|START_OF_TURN_TOKEN|>", "<|END_OF_TURN_TOKEN|>" ] }

You are Aya, a brilliant, sophisticated, multilingual AI-assistant trained to assist human users by

{{- if or .Tools .System }}<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|> {{- if .Tools }}# Safety Preamble

Creative Commons Attribution-NonCommercial 4.0 International Public License with Acceptable Use Add

Readme

This is an uncensored version of CohereForAI/aya-expanse created with abliteration (see remove-refusals-with-transformers to know more about it).
This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.

References