Add pipeline_tag and link to technical report
#1
by
nielsr
HF Staff
- opened
README.md
CHANGED
|
@@ -1,8 +1,9 @@
|
|
| 1 |
---
|
| 2 |
-
license: mit
|
| 3 |
base_model:
|
| 4 |
- XiaomiMiMo/MiMo-V2-Flash-Base
|
| 5 |
library_name: transformers
|
|
|
|
|
|
|
| 6 |
---
|
| 7 |
|
| 8 |
<br/><br/>
|
|
@@ -20,10 +21,12 @@ library_name: transformers
|
|
| 20 |
|
|
| 21 |
<a href="https://huggingface.co/XiaomiMiMo/MiMo-V2-Flash" target="_blank">π€ HuggingFace</a>
|
| 22 |
|
|
| 23 |
-
<a href="https://
|
| 24 |
|
|
| 25 |
<a href="https://mimo.xiaomi.com/blog/mimo-v2-flash" target="_blank">π° Blog </a>
|
| 26 |
|
|
|
|
|
|
|
|
| 27 |
<br/><br/>
|
| 28 |
<strong>Play around!</strong>
|
| 29 |
<a href="https://aistudio.xiaomimimo.com" target="_blank">π¨οΈ Xiaomi MiMo Studio </a>
|
|
@@ -36,6 +39,8 @@ library_name: transformers
|
|
| 36 |
|
| 37 |
**MiMo-V2-Flash** is a Mixture-of-Experts (MoE) language model with **309B total parameters** and **15B active parameters**. Designed for high-speed reasoning and agentic workflows, it utilizes a novel hybrid attention architecture and Multi-Token Prediction (MTP) to achieve state-of-the-art performance while significantly reducing inference costs.
|
| 38 |
|
|
|
|
|
|
|
| 39 |
<p align="center">
|
| 40 |
<img width="80%" src="https://github.com/XiaomiMiMo/MiMo-V2-Flash/raw/main/figures/MiMo-v2-flash-performance.jpg?raw=true">
|
| 41 |
</p>
|
|
@@ -304,7 +309,7 @@ If you find our work helpful, please cite our technical report:
|
|
| 304 |
title={MiMo-V2-Flash Technical Report},
|
| 305 |
author={LLM-Core Xiaomi},
|
| 306 |
year={2025},
|
| 307 |
-
url={https://
|
| 308 |
}
|
| 309 |
```
|
| 310 |
|
|
@@ -317,4 +322,4 @@ Please contact us at [mimo@xiaomi.com](mailto:mimo@xiaomi.com), join our WeChat
|
|
| 317 |
<img src="https://github.com/XiaomiMiMo/MiMo-V2-Flash/raw/main/figures/wechat_group/wechat2.jpg?raw=true" width="20%" />
|
| 318 |
<img src="https://github.com/XiaomiMiMo/MiMo-V2-Flash/raw/main/figures/wechat_group/wechat3.jpg?raw=true" width="20%" />
|
| 319 |
<img src="https://github.com/XiaomiMiMo/MiMo-V2-Flash/raw/main/figures/wechat_group/wechat4.jpg?raw=true" width="20%" />
|
| 320 |
-
</p>
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
base_model:
|
| 3 |
- XiaomiMiMo/MiMo-V2-Flash-Base
|
| 4 |
library_name: transformers
|
| 5 |
+
license: mit
|
| 6 |
+
pipeline_tag: text-generation
|
| 7 |
---
|
| 8 |
|
| 9 |
<br/><br/>
|
|
|
|
| 21 |
|
|
| 22 |
<a href="https://huggingface.co/XiaomiMiMo/MiMo-V2-Flash" target="_blank">π€ HuggingFace</a>
|
| 23 |
|
|
| 24 |
+
<a href="https://huggingface.co/papers/2601.02780" target="_blank">π Technical Report </a>
|
| 25 |
|
|
| 26 |
<a href="https://mimo.xiaomi.com/blog/mimo-v2-flash" target="_blank">π° Blog </a>
|
| 27 |
|
|
| 28 |
+
<a href="https://github.com/XiaomiMiMo/MiMo-V2-Flash" target="_blank">π» GitHub </a>
|
| 29 |
+
|
|
| 30 |
<br/><br/>
|
| 31 |
<strong>Play around!</strong>
|
| 32 |
<a href="https://aistudio.xiaomimimo.com" target="_blank">π¨οΈ Xiaomi MiMo Studio </a>
|
|
|
|
| 39 |
|
| 40 |
**MiMo-V2-Flash** is a Mixture-of-Experts (MoE) language model with **309B total parameters** and **15B active parameters**. Designed for high-speed reasoning and agentic workflows, it utilizes a novel hybrid attention architecture and Multi-Token Prediction (MTP) to achieve state-of-the-art performance while significantly reducing inference costs.
|
| 41 |
|
| 42 |
+
The model was presented in the [MiMo-V2-Flash Technical Report](https://huggingface.co/papers/2601.02780).
|
| 43 |
+
|
| 44 |
<p align="center">
|
| 45 |
<img width="80%" src="https://github.com/XiaomiMiMo/MiMo-V2-Flash/raw/main/figures/MiMo-v2-flash-performance.jpg?raw=true">
|
| 46 |
</p>
|
|
|
|
| 309 |
title={MiMo-V2-Flash Technical Report},
|
| 310 |
author={LLM-Core Xiaomi},
|
| 311 |
year={2025},
|
| 312 |
+
url={https://huggingface.co/papers/2601.02780}
|
| 313 |
}
|
| 314 |
```
|
| 315 |
|
|
|
|
| 322 |
<img src="https://github.com/XiaomiMiMo/MiMo-V2-Flash/raw/main/figures/wechat_group/wechat2.jpg?raw=true" width="20%" />
|
| 323 |
<img src="https://github.com/XiaomiMiMo/MiMo-V2-Flash/raw/main/figures/wechat_group/wechat3.jpg?raw=true" width="20%" />
|
| 324 |
<img src="https://github.com/XiaomiMiMo/MiMo-V2-Flash/raw/main/figures/wechat_group/wechat4.jpg?raw=true" width="20%" />
|
| 325 |
+
</p>
|