Add pipeline tag, library, license and link to code
Browse filesThis PR adds missing metadata to the model card: `pipeline_tag`, `library_name`, and `license`. It also adds a link to the Github repository.
README.md
CHANGED
@@ -1,11 +1,17 @@
|
|
1 |
---
|
|
|
|
|
2 |
datasets:
|
3 |
- QizhiPei/MathFusionQA
|
4 |
language:
|
5 |
- en
|
6 |
-
|
7 |
-
|
|
|
8 |
---
|
9 |
|
|
|
|
|
|
|
10 |
|
11 |
-
|
|
|
1 |
---
|
2 |
+
base_model:
|
3 |
+
- deepseek-ai/deepseek-math-7b-base
|
4 |
datasets:
|
5 |
- QizhiPei/MathFusionQA
|
6 |
language:
|
7 |
- en
|
8 |
+
pipeline_tag: question-answering
|
9 |
+
library_name: transformers
|
10 |
+
license: mit
|
11 |
---
|
12 |
|
13 |
+
Paper: [MathFusion: Enhancing Mathematic Problem-solving of LLM through Instruction Fusion](https://arxiv.org/abs/2503.16212)
|
14 |
+
|
15 |
+
This model, `DeepSeekMath-7B-MathFusion`, is a fine-tuned version of `deepseek-ai/deepseek-math-7b-base` trained on the `QizhiPei/MathFusionQA` dataset. It's designed for question-answering tasks, particularly in the domain of mathematics.
|
16 |
|
17 |
+
Code: https://github.com/QizhiPei/MathFusion
|