---
license: other
license_name: qwen
license_link: https://huggingface.co/Qwen/Qwen2.5-72B/raw/main/LICENSE
library_name: transformers
language:
- en
tags:
- chat
- conversational
base_model:
- Qwen/Qwen2.5-72B
- Skywork/MindLink-72B-0801
- Unbabel/Tower-Plus-72B
- EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2
pipeline_tags:
- text-generation
- conversational
- chat

---

![image/png](https://cdn-uploads.huggingface.co/production/uploads/65b19c1b098c85365af5a83e/r7maKU1wOkmSyHf-qPlMz.png)

[GGUF](https://huggingface.co/mradermacher/Eva-Mindlink-72b-GGUF) [iMat](https://huggingface.co/mradermacher/Eva-Mindlink-72b-i1-GGUF)

# Eva Mindlink 72B

Eva Mindlink 72B is a *normalized denoised fourier interpolation* of the following models:

```yaml
output_base_model: "Qwen/Qwen2.5-72B"
output_dtype: "bfloat16"
finetune_merge:
  - { "model": "Skywork/MindLink-72B-0801", "base": "Qwen/Qwen2.5-72B", "alpha": 0.9, "is_input": true }
  - { "model": "Unbabel/Tower-Plus-72B", "base": "Qwen/Qwen2.5-72B", "alpha": 0.5 }
  - { "model": "EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2", "base": "Qwen/Qwen2.5-72B", "alpha": 0.8, "is_output": true }
```

In other words, all of these models get warped and interpolated in signal space, and then jammed back on top of the base model (which in this case was Qwen2.5-72B); with the MindLink-72B-0801 input layer and the EVA-Qwen2.5-72B-v0.2 output layer.

## Citation

If you find our work helpful, feel free to give us a cite.

```
@misc{eva-mindlink-72b,
    title = {Eva Mindlink 72B},
    url = {https://huggingface.co/maldv/Eva-Mindlink-72B},
    author = {Praxis Maldevide},
    month = {August},
    year = {2025}
}
```