This is a merge of pre-trained language models created using
mergekit.
This model was merged using the
DARE TIES merge method using
Replete-AI/Replete-LLM-V2.5-Qwen-3b as a base.
1models:
2 - model: Replete-AI/Replete-LLM-V2.5-Qwen-3b+bunnycore/qwen-2.5-3b-lora_model
3 parameters:
4 density: 0.5
5 weight: 0.5
6 - model: unsloth/Qwen2.5-3B-Instruct+bunnycore/qwen-2.5-3b-lora_model
7 parameters:
8 density: 0.5
9 weight: 0.5
10
11merge_method: dare_ties
12base_model: Replete-AI/Replete-LLM-V2.5-Qwen-3b
13parameters:
14 normalize: false
15 int8_mask: true
16dtype: float16
