metadata

base_model:
  - cognitivecomputations/dolphin-2.9.1-qwen-110b
  - Qwen/Qwen1.5-110B-Chat
library_name: transformers
tags:
  - mergekit
  - merge

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the linear DARE merge method using cognitivecomputations/dolphin-2.9.1-qwen-110b as a base.

Models Merged

The following models were included in the merge:

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