huihui_ai/granite3.1-dense-abliterated

huihui_ai/

granite3.1-dense-abliterated

810 Downloads Updated 9 months ago

The IBM Granite 2B and 8B models are text-only dense LLMs trained on over 12 trillion tokens of data, demonstrated significant improvements over their predecessors in performance and speed in IBM’s initial testing.

tools 2b 8b

Name

11 models

Size

Context

Input

granite3.1-dense-abliterated:latest

4.9GB · 128K context window · Text · 9 months ago

granite3.1-dense-abliterated:latest

4.9GB

128K

Text

granite3.1-dense-abliterated:2b

1.5GB · 128K context window · Text · 9 months ago

granite3.1-dense-abliterated:2b

1.5GB

128K

Text

granite3.1-dense-abliterated:8b

4.9GB · 128K context window · Text · 9 months ago

granite3.1-dense-abliterated:8b latest

4.9GB

128K

Text

This is an uncensored version of ibm-granite/granite-31-language-models 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.