README.md

metadata

base_model:
  - Qwen/QwQ-32B-Preview
  - Qwen/Qwen2.5-Coder-32B-Instruct
  - EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2
library_name: transformers
tags:
  - mergekit
  - merge

my kofi:

https://ko-fi.com/ogodwin10 If you like this model, please give me some sponsorship and I will continue to create better merges. If there is a device that can fine-tune the model, there will be more new models fine-tuned after the merge (just like solar 10b).

merge

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

Merge Details

Merge Method

This model was merged using the TIES merge method using EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2 as a base.

Models Merged

The following models were included in the merge:

• Qwen/QwQ-32B-Preview
• Qwen/Qwen2.5-Coder-32B-Instruct

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Qwen/QwQ-32B-Preview
    parameters:
      density: 1
      weight: 1 
  - model: Qwen/Qwen2.5-Coder-32B-Instruct
    parameters:
      density: 1
      weight: 1 
      
  - model: EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2
    parameters:
      density: 1
      weight: 1 
      
  - model: Qwen/QwQ-32B-Preview
    parameters:
      density: 1
      weight: 1 
      
  - model: Qwen/Qwen2.5-Coder-32B-Instruct
    parameters:
      density: 1
      weight: 1 
      
  - model: EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2
    parameters:
      density: 1
      weight: 1 

merge_method: ties
base_model: EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2
parameters:
  normalize: false
  int8_mask: true
dtype: bfloat16