matatonic/QwQ-32B-Coder-Fusion-7030-4.25bpw-exl2

huihui-ai/QwQ-32B-Coder-Fusion-7030

Overview

QwQ-32B-Coder-Fusion-78030 is a mixed model that combines the strengths of two powerful Qwen-based models: huihui-ai/QwQ-32B-Preview-abliterated and huihui-ai/Qwen2.5-Coder-32B-Instruct-abliterated.
The weights are blended in a 7:3 ratio, with 70% of the weights from QwQ-32B-Preview-abliterated and 30% from the abliterated Qwen2.5-Coder-32B-Instruct-abliterated model. Although it's a simple mix, the model is usable, and no gibberish has appeared. This is an experiment. I test the 9:1, 8:2, and 7:3 ratios separately to see how much impact they have on the model.

Please refer to the mixed source code.

Model Details

• Base Models:
  • huihui-ai/QwQ-32B-Preview-abliterated (70%)
  • huihui-ai/Qwen2.5-Coder-32B-Instruct-abliterated (30%)
• Model Size: 32B parameters
• Architecture: Qwen 2.5
• Mixing Ratio: 7:3 (QwQ-32B-Preview-abliterated:Qwen2.5-Coder-32B-Instruct-abliterated)

ollama

You can use huihui_ai/qwq-fusion:32b-7030 directly,

ollama run huihui_ai/qwq-fusion:32b-7030

Other proportions can be obtained by visiting huihui_ai/qwq-fusion.