This is a merge of pre-trained language models created using
mergekit.
This model was merged using the
DARE TIES merge method using
meta-llama/Llama-3.2-1B-Instruct as a base.
1base_model: meta-llama/Llama-3.2-1B-Instruct
2dtype: bfloat16
3merge_method: dare_ties
4models:
5- model: meta-llama/Llama-3.2-1B-Instruct
6 parameters:
7 density: 0.35
8 weight: 1.0
9- model: ai-nexuz/llama-3.2-1b-instruct-fine-tuned
10 parameters:
11 density: 0.35
12 weight: 0.9
13- model: FuseAI/FuseChat-Llama-3.2-1B-SFT
14 parameters:
15 density: 0.35
16 weight: 0.4
17out_dtype: bfloat16
18parameters:
19 int8_mask: true
20
