Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: llama3.2
|
3 |
+
datasets:
|
4 |
+
- LLM360/MegaMath
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
pipeline_tag: text-generation
|
8 |
+
library_name: transformers
|
9 |
+
tags:
|
10 |
+
- math
|
11 |
+
- code
|
12 |
+
- cot
|
13 |
+
- pal
|
14 |
+
---
|
15 |
+
|
16 |
+
# MegaMath-Llama-3.2-3B
|
17 |
+
|
18 |
+
A proof-of-concept model train on [MegaMath](https://huggingface.co/datasets/LLM360/MegaMath) dataset, capable of both Chain-of-Thought and Program-Aided-Language problem solving.
|
19 |
+
|
20 |
+

|
21 |
+
|
22 |
+
## Performance
|
23 |
+
|
24 |
+
|
25 |
+

|
26 |
+
|
27 |
+
## Citation
|
28 |
+
If you find our work useful, please cite
|
29 |
+
```bibtex
|
30 |
+
@article{zhou2025megamath,
|
31 |
+
title = {MegaMath: Pushing the Limits of Open Math Corpora},
|
32 |
+
author = {Zhou, Fan and Wang, Zengzhi and Ranjan, Nikhil and Cheng, Zhoujun and Tang, Liping and He, Guowei and Liu, Zhengzhong and Xing, Eric P.},
|
33 |
+
journal = {arXiv preprint arXiv:2504.xxxxx},
|
34 |
+
year = {2025},
|
35 |
+
note = {Preprint}
|
36 |
+
}
|
37 |
+
```
|