Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,26 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- MathGenie/MathCode-Pile
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
base_model:
|
| 10 |
+
- codellama/CodeLlama-7b-hf
|
| 11 |
+
pipeline_tag: text-generation
|
| 12 |
+
tags:
|
| 13 |
+
- math
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
# MathCoder2
|
| 17 |
+
|
| 18 |
+
### Introduction
|
| 19 |
+
|
| 20 |
+
The MathCoder2 models are created by conducting continued pretraining on [MathCode-Pile](https://huggingface.co/datasets/MathGenie/MathCode-Pile). They are introduced in the paper [MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Code](link/to/paper).
|
| 21 |
+
|
| 22 |
+
The mathematical pretraining dataset includes mathematical code accompanied with natural language reasoning steps, making it a superior resource for models aimed at performing advanced mathematical reasoning tasks.
|
| 23 |
+
|
| 24 |
+
### Evaluation
|
| 25 |
+
|
| 26 |
+
|