Commit
•
94c2d88
1
Parent(s):
5731bb4
Update README.md
Browse files
README.md
CHANGED
|
@@ -15,14 +15,13 @@ Code: [https://github.com/TIGER-AI-Lab/MAmmoTH](https://github.com/TIGER-AI-Lab/
|
|
| 15 |
## Introduction
|
| 16 |
We introduce 🦣MAmmoTH, a series of open-source large language models (LLMs) specifically tailored for general math problem-solving. The MAmmoTH models are trained on 🤗 [MathInstruct Dataset](https://huggingface.co/datasets/TIGER-Lab/MathInstruct), a meticulously curated instruction tuning dataset that is lightweight yet generalizable. MathInstruct is compiled from 13 math rationale datasets, six of which are newly curated by this work. It uniquely focuses on the hybrid use of chain-of-thought (CoT) and program-of-thought (PoT) rationales, and ensures extensive coverage of diverse mathematical fields.
|
| 17 |
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
|
|
| 21 |
-
|
| 22 |
-
|
|
| 23 |
-
|
|
| 24 |
-
|
|
| 25 |
-
| 70B | 🦣[MAmmoTH-70B](https://huggingface.co/TIGER-Lab/MAmmoTH-70B) | - |
|
| 26 |
|
| 27 |
|
| 28 |
## Training Data
|
|
@@ -37,7 +36,7 @@ The models are evaluated using open-ended and multiple-choice math problems from
|
|
| 37 |
|
| 38 |
|
| 39 |
| Model | Size | Base | GSM8K | MATH | AQuA | NumGLUE | IID Avg | SVAMP | Mathematics | SimulEq | SAT-Math | MMLU-Math | OOD Avg |
|
| 40 |
-
|
| 41 |
| | | | | | | | | | | | | | |
|
| 42 |
| MAmmoTH | 7B | Llama-2 | 51.7 | 31.2 | 42.9 | 53.1 | 44.7 | 66.7 | 44.8 | 42 | 36.4 | 38.6 | 45.7 |
|
| 43 |
| MAmmoTH-Coder | 7B | Code-Llama | 58.8 | 35.2 | 43 | 57.1 | 48.5 | 71.1 | 53.9 | 44.6 | 40 | 40.5 | 50.2 |
|
|
|
|
| 15 |
## Introduction
|
| 16 |
We introduce 🦣MAmmoTH, a series of open-source large language models (LLMs) specifically tailored for general math problem-solving. The MAmmoTH models are trained on 🤗 [MathInstruct Dataset](https://huggingface.co/datasets/TIGER-Lab/MathInstruct), a meticulously curated instruction tuning dataset that is lightweight yet generalizable. MathInstruct is compiled from 13 math rationale datasets, six of which are newly curated by this work. It uniquely focuses on the hybrid use of chain-of-thought (CoT) and program-of-thought (PoT) rationales, and ensures extensive coverage of diverse mathematical fields.
|
| 17 |
|
| 18 |
+
| | **Base Model: Llama-2** | **Base Model: Code Llama** |
|
| 19 |
+
|-----|---------------------------------------------------------------|--------------------------------------------------------------------------|
|
| 20 |
+
| 7B | 🦣[MAmmoTH-7B](https://huggingface.co/TIGER-Lab/MAmmoTH-7B) | 🦣[MAmmoTH-Coder-7B](https://huggingface.co/TIGER-Lab/MAmmoTH-Coder-7B) |
|
| 21 |
+
| 13B | 🦣[MAmmoTH-13B](https://huggingface.co/TIGER-Lab/MAmmoTH-13B) | 🦣[MAmmoTH-Coder-13B](https://huggingface.co/TIGER-Lab/MAmmoTH-Coder-13B)|
|
| 22 |
+
| 34B | - | 🦣[MAmmoTH-Coder-34B](https://huggingface.co/TIGER-Lab/MAmmoTH-Coder-34B)|
|
| 23 |
+
| 70B | 🦣[MAmmoTH-70B](https://huggingface.co/TIGER-Lab/MAmmoTH-70B) | - |
|
| 24 |
+
|
|
|
|
|
| 25 |
|
| 26 |
|
| 27 |
## Training Data
|
|
|
|
| 36 |
|
| 37 |
|
| 38 |
| Model | Size | Base | GSM8K | MATH | AQuA | NumGLUE | IID Avg | SVAMP | Mathematics | SimulEq | SAT-Math | MMLU-Math | OOD Avg |
|
| 39 |
+
|-------------------|-------|---------------|-----------|-------|-------|-----------|---------------|-----------|---------------|-----------|-----------|---------------|---------------|
|
| 40 |
| | | | | | | | | | | | | | |
|
| 41 |
| MAmmoTH | 7B | Llama-2 | 51.7 | 31.2 | 42.9 | 53.1 | 44.7 | 66.7 | 44.8 | 42 | 36.4 | 38.6 | 45.7 |
|
| 42 |
| MAmmoTH-Coder | 7B | Code-Llama | 58.8 | 35.2 | 43 | 57.1 | 48.5 | 71.1 | 53.9 | 44.6 | 40 | 40.5 | 50.2 |
|