Add pipeline_tag and link to technical report

#1
by nielsr HF Staff - opened
Files changed (1) hide show
  1. README.md +9 -4
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">πŸ€— HuggingFace</a>
22
  &nbsp;|
23
- <a href="https://github.com/XiaomiMiMo/MiMo-V2-Flash/blob/main/paper.pdf" target="_blank">πŸ“” Technical Report </a>
24
  &nbsp;|
25
  <a href="https://mimo.xiaomi.com/blog/mimo-v2-flash" target="_blank">πŸ“° Blog </a>
26
  &nbsp;|
 
 
27
  <br/><br/>
28
  <strong>Play around!</strong> &nbsp;
29
  <a href="https://aistudio.xiaomimimo.com" target="_blank">πŸ—¨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://github.com/XiaomiMiMo/MiMo-V2-Flash/paper.pdf}
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">πŸ€— HuggingFace</a>
23
  &nbsp;|
24
+ <a href="https://huggingface.co/papers/2601.02780" target="_blank">πŸ“” Technical Report </a>
25
  &nbsp;|
26
  <a href="https://mimo.xiaomi.com/blog/mimo-v2-flash" target="_blank">πŸ“° Blog </a>
27
  &nbsp;|
28
+ <a href="https://github.com/XiaomiMiMo/MiMo-V2-Flash" target="_blank">πŸ’» GitHub </a>
29
+ &nbsp;|
30
  <br/><br/>
31
  <strong>Play around!</strong> &nbsp;
32
  <a href="https://aistudio.xiaomimimo.com" target="_blank">πŸ—¨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>