---
title: deepseek-r1-qwen-2.5-32B-ablated
canonical_url: "https://www.modelscope.cn/models/NaniDAO/deepseek-r1-qwen-2.5-32B-ablated"
md_url: "https://www.modelscope.cn/models/NaniDAO/deepseek-r1-qwen-2.5-32B-ablated.md"
repository: NaniDAO/deepseek-r1-qwen-2.5-32B-ablated
last_updated: 2025-01-25
license: mit
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - qwen2
architectures:
  - Qwen2ForCausalLM
base_model:
  - deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
base_model_relation: finetune
parameters: 32.8B
tensor_type:
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 1035
stars: 0
tags:
  - ablated
  - ablation
  - abliterated
  - uncensored
  - nani
  - reasoning
  - qwen
  - deepseek
---

# deepseek-r1-qwen-2.5-32B-ablated

> deepseek-r1-qwen-2.5-32B-ablated - NaniDAO 在 ModelScope 开源的模型。DeepSeek-R1-Distill-Qwen-32B with ablation technique applied for a more helpful (and based) reasoning model.

NaniDAO/deepseek-r1-qwen-2.5-32B-ablated 是 ModelScope 魔搭社区上的 32.8B 参数text-generation模型，采用 mit 许可，基于 deepseek-ai/DeepSeek-R1-Distill-Qwen-32B 构建，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: NaniDAO/deepseek-r1-qwen-2.5-32B-ablated
- **License**: mit
- **Tasks**: text-generation
- **Parameters**: 32.8B
- **Base model**: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: ablated, ablation, abliterated, uncensored, nani, reasoning, qwen, deepseek
- **Downloads**: 1035
- **Stars**: 0
- **Last updated**: 2025-01-25

Source: https://www.modelscope.cn/models/NaniDAO/deepseek-r1-qwen-2.5-32B-ablated

---

# naniseek

[DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B) with [ablation](https://www.lesswrong.com/posts/jGuXSZgv6qfdhMCuJ/refusal-in-llms-is-mediated-by-a-single-direction) technique applied for a more helpful (and based) reasoning model.

This means it will refuse less of your valid requests for an uncensored UX. *Use responsibly and use common sense.* 

We do not take any responsibility for how you apply this intelligence, *just as we do not for how you apply your own.*

[Join the nani discord](https://t.co/UMELOqZlSO) to discuss and improve applications of this model together. Follow for more updates on X: [@nani__ooo](https://x.com/nani__ooo).

![image/png](https://cdn-uploads.huggingface.co/production/uploads/6587d8dd1b44d0e694104fbf/0dkt6EhZYwXVBxvSWXdaM.png)