metadata

pipeline_tag: text-generation
inference: false
license: apache-2.0
library_name: transformers
tags:
  - language
  - granite-3.1
  - abliterated
  - uncensored
base_model:
  - ibm-granite/granite-3.1-2b-instruct

huihui-ai/granite-3.1-2b-instruct-abliterated

This is an uncensored version of ibm-granite/granite-3.1-2b-instruct 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.

Use with ollama

You can use huihui_ai/granite3.1-dense-abliterated directly,

ollama run huihui_ai/granite3.1-dense-abliterated:2b