Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
Paper
• 2311.03099 • Published
• 30
This is a merge of pre-trained language models created using mergekit.
This model was merged using the DARE TIES merge method using ReadyArt/Forgotten-Safeword-24B-v4.0 as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: ReadyArt/Forgotten-Safeword-24B-v4.0
parameters:
weight: 0.5
density: 0.35
- model: TroyDoesAI/BlackSheep-24B
parameters:
weight: 0.5
density: 0.35
merge_method: dare_ties
base_model: ReadyArt/Forgotten-Safeword-24B-v4.0
parameters:
normalize: true
int8_mask: true
temperature: 2.5
tokenizer_source: union
dtype: bfloat16
chat_template: auto