saucam/aqua-qwen-0.1-110B

aqua-qwen-0.1-110B

This model was created by merging 2 models using the linear DARE merge method using mergekit. The following models were included in the merge:

• cognitivecomputations/dolphin-2.9.1-qwen-110b as a base.
• Qwen/Qwen1.5-110B-Chat

Configuration

The following YAML configuration was used to produce this model:

name: aqua-qwen-0.1-110B
base_model:
  model:
   path: cognitivecomputations/dolphin-2.9.1-qwen-110b
dtype: bfloat16
merge_method: dare_linear
parameters:
  normalize: 1.0
slices:
  - sources:
    - model: cognitivecomputations/dolphin-2.9.1-qwen-110b
      layer_range: [0, 80]
      parameters:
        weight: 0.6
    - model: Qwen/Qwen1.5-110B-Chat
      layer_range: [0, 80]
      parameters:
        weight: 0.4

Usage

It is recommended to use GGUF version of the model available here