---
license: mit
library_name: transformers
base_model:
- deepseek-ai/DeepSeek-V3-0324
- deepseek-ai/DeepSeek-R1
- deepseek-ai/DeepSeek-R1-0528
pipeline_tag: text-generation
---
# DeepSeek-TNG-R1T2-Chimera

<div align="center">
<img src="https://354918363417-runtime-assets.s3.eu-central-1.amazonaws.com/company_logo_light.svg"
     alt="TNG Logo" 
     width="400"
     style="display: inline-block; vertical-align: middle;"/>
</div>
<br>
<div align="center">
  <a href="LICENSE" style="margin: 2px;">
    <img alt="License" src="https://img.shields.io/badge/License-MIT-f5de53?&color=f5de53" style="display: inline-block; vertical-align: middle;"/>
  </a>
</div>
<br>
<div align="center">
  <a href="https://x.com/tngtech/status/1916284566127444468" style="margin: 2px;">
    <img alt="Benchmarks" src="R1T-Chimera_Benchmarks_20250427_V1.jpg" style="display: inline-block; vertical-align: middle;"/>
  </a>
</div>

**Assembly of Experts construction of a Chimera model based on the [DeepSeek-R1-0528](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528), [DeepSeek-R1](https://huggingface.co/deepseek-ai/DeepSeek-R1) and [DeepSeek-V3-0324](https://huggingface.co/deepseek-ai/DeepSeek-V3-0324) parent models**

We present the "DeepSeek-TNG R1T2 Chimera" 671B model, the successor to our original "DeepSeek R1T Chimera" released on April 26th. 

Unlike the original Chimera, which was based on the two parent models V3-0324 and R1, the new Chimera is a Trimind with three parents, additionally R1-0528. It is constructed using the Assembly of Experts-method with relatively fine-granular direct brain edits. This more refined assembly allowed fixing the &lt;think&gt; token consistency issue, which was a weakness of R1T and is now solved for R1T2. 

R1T2 operates at a new sweet spot in intelligence vs. output token length:

IMAGE

For details on the construction process, please [read our paper](https://arxiv.org/abs/2506.14794). 

[Paper on arXiV](https://arxiv.org/abs/2506.14794)


## Model Details

- **Architecture**: DeepSeek-MoE transformer-based language model
- **Combination Method**: Assembly of Experts from DeepSeek-R1-0528, DeepSeek-R1 and DeepSeek-V3-0324 parent models
- **Release Date**: 2025-07-02

## Use, Out-of-scope Use, Limitations, Risks, Recommendations et al.
Regarding R1T2-Chimera, we ask you to follow the careful guidelines that Microsoft has created for their "MAI-DS-R1" DeepSeek-based model. 

These guidelines are available [here on Hugging Face](https://huggingface.co/microsoft/MAI-DS-R1).

## Contact

- Email: research@tngtech.com
- X.com: @tngtech

## Citation

```
@misc{tng_technology_consulting_gmbh_2025_07_0x,
	author       = { TNG Technology Consulting GmbH },
	title        = { DeepSeek-TNG-R1T2-Chimera },
	year         = 2025,
    month        = { July },
	url          = { https://huggingface.co/tngtech/DeepSeek-TNG-R1T2-Chimera },
	doi          = { xxx },
	publisher    = { Hugging Face }
}
```