Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# M2-Reasoning: Empowering MLLMs with Unified General and Spatial Reasoning
|
| 2 |
|
| 3 |
π [Technical Report]() | π€ [Hugging Face](https://huggingface.co/inclusionAI/M2-Reasoning)ο½ π€ [ModelScope](https://www.modelscope.cn/models/inclusionAI/M2-Reasoning)
|
|
@@ -300,4 +314,4 @@ If you find our work helpful, feel free to give us a cite.
|
|
| 300 |
year = {2025},
|
| 301 |
archivePrefix = {arXiv},
|
| 302 |
}
|
| 303 |
-
```
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
datasets:
|
| 4 |
+
- AI4Math/MathVista
|
| 5 |
+
- MathLLMs/MathVision
|
| 6 |
+
- AI4Math/MathVerse
|
| 7 |
+
- Racktic/dynamath
|
| 8 |
+
- lscpku/LogicVista
|
| 9 |
+
- nyu-visionx/CV-Bench
|
| 10 |
+
- nyu-visionx/VSI-Bench
|
| 11 |
+
base_model:
|
| 12 |
+
- Qwen/Qwen2.5-VL-7B-Instruct
|
| 13 |
+
pipeline_tag: image-text-to-text
|
| 14 |
+
---
|
| 15 |
# M2-Reasoning: Empowering MLLMs with Unified General and Spatial Reasoning
|
| 16 |
|
| 17 |
π [Technical Report]() | π€ [Hugging Face](https://huggingface.co/inclusionAI/M2-Reasoning)ο½ π€ [ModelScope](https://www.modelscope.cn/models/inclusionAI/M2-Reasoning)
|
|
|
|
| 314 |
year = {2025},
|
| 315 |
archivePrefix = {arXiv},
|
| 316 |
}
|
| 317 |
+
```
|