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
624 Pulls Updated 4 months ago
Updated 4 months ago
4 months ago
6567faf671e9 · 4.9GB
model
archgranite
·
parameters8.17B
·
quantizationQ4_K_M
4.9GB
system
Knowledge Cutoff Date: April 2024.
You are Granite, developed by IBM.
69B
template
<|start_of_role|>system<|end_of_role|>
{{- if and (gt (len .Messages) 0) (eq (index .Messages 0).Rol
1.4kB
license
Apache License
Version 2.0, January 2004
11kB
Readme
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.