This is a merge of pre-trained language models created using
mergekit.
This model was merged using the
DARE TIES merge method using
mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated as a base.
1models:
2 - model: mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated
3 # No parameters necessary for base model
4 - model: netcat420/MFANNv0.19
5 parameters:
6 density: 0.53
7 weight: 0.5
8merge_method: dare_ties
9base_model: mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated
10parameters:
11 int8_mask: true
12dtype: bfloat16
13
