This model was created by merging 2 models using the linear
DARE merge method
using
mergekit.
The following models were included in the merge:
1name: aqua-qwen-0.1-110B
2base_model:
3 model:
4 path: cognitivecomputations/dolphin-2.9.1-qwen-110b
5dtype: bfloat16
6merge_method: dare_linear
7parameters:
8 normalize: 1.0
9slices:
10 - sources:
11 - model: cognitivecomputations/dolphin-2.9.1-qwen-110b
12 layer_range: [0, 80]
13 parameters:
14 weight: 0.6
15 - model: Qwen/Qwen1.5-110B-Chat
16 layer_range: [0, 80]
17 parameters:
18 weight: 0.4
It is recommended to use GGUF version of the model
available here
