metadata

license: apache-2.0
language:
  - en
pipeline_tag: text-generation
base_model:
  - huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated
  - huihui-ai/QwQ-32B-Preview-abliterated
  - huihui-ai/Sky-T1-32B-Preview-abliterated
tags:
  - chat
  - abliterated
  - uncensored
  - Fusion
library_name: transformers

huihui-ai/DeepSeekR1-QwQ-SkyT1-32B-Fusion-622

Overview

DeepSeekR1-QwQ-SkyT1-32B-Fusion-622 is a mixed model that combines the strengths of three powerful Qwen-based models: huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated, huihui-ai/QwQ-32B-Preview-abliterated and huihui-ai/Sky-T1-32B-Preview-abliterated

Although it's a simple mix, the model is usable, and no gibberish has appeared.

This is a test. I test the 80:10:10, 70:15:15 and 60:20:20 ratios separately to see how much impact they have on the model.

Model Details

Base Models:
Model Size: 32B parameters
Architecture: Qwen 2.5

Use with ollama

You can use huihui_ai/deepseekr1-qwq-skyt1-fusion directly

ollama run huihui_ai/deepseekr1-qwq-skyt1-fusion:622