---
base_model:
- cognitivecomputations/dolphin-2.9.1-qwen-110b
- Qwen/Qwen1.5-110B-Chat
library_name: transformers
tags:
- mergekit
- merge
license: apache-2.0
language:
- en
---
## aqua-qwen-0.1-110B

This model was created by merging 2 models using the linear [DARE](https://arxiv.org/abs/2311.03099) merge method 
using [mergekit](https://github.com/arcee-ai/mergekit).
The following models were included in the merge:

- [cognitivecomputations/dolphin-2.9.1-qwen-110b](https://huggingface.co/cognitivecomputations/dolphin-2.9.1-qwen-110b) as a base.
- [Qwen/Qwen1.5-110B-Chat](https://huggingface.co/Qwen/Qwen1.5-110B-Chat)


## Configuration

The following YAML configuration was used to produce this model:

```yaml
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](https://huggingface.co/saucam/aqua-qwen-0.1-110B-GGUF/blob/main/README.md)