---
base_model: dnotitia/Smoothie-Qwen3-8B
library_name: transformers
pipeline_tag: text-generation
license: apache-2.0
---

<p align="center">
<img src="https://huggingface.co/dnotitia/DNA-2.0-14B/resolve/main/assets/dna-2.0-logo.png" width="400" style="margin: 40px auto;">
</p>

# DNA 2.0

We introduce **DNA 2.0**, a latest advanced model that builds upon our innovative [Smoothie Qwen3](https://huggingface.co/collections/dnotitia/smoothie-qwen3-6811896ebb3a255de7b5b437) model with enhanced various capabilities. By reducing Chinese token emission probabilities in the base Qwen3 model and applying uncensored training methodology inspired by [Perplexity R1 1776](https://www.perplexity.ai/hub/blog/open-sourcing-r1-1776), we've created a model that excels in analytical reasoning while maintaining genuinely open conversational capabilities.

> [!Note]
> This is a **PRIVATE MODEL** and is not available for public download.
> If you're looking for a public version, please check out [DNA 2.0 14B](https://huggingface.co/dnotitia/DNA-2.0-14B) instead.