granite-3.1-2b-instruct-abliterated/README.md

pipeline_tag, inference, license, library_name, tags, base_model

pipeline_tag	inference	license	library_name	tags	base_model
text-generation	false	apache-2.0	transformers	language granite-3.1 abliterated uncensored	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