Commit
•
b9b5125
1
Parent(s):
b20da88
Update README.md
Browse files
README.md
CHANGED
|
@@ -20,8 +20,6 @@ This repo provides the official implementation of **SuperCorrect** a novel two-
|
|
| 20 |
|
| 21 |
Notably, our **SupperCorrect-7B** model significantly surpasses powerful **DeepSeekMath-7B by 7.8%/5.3% and Qwen2.5-Math-7B by 15.1%/6.3% on MATH/GSM8K benchmarks**, achieving new SOTA performance among all 7B models.
|
| 22 |
|
| 23 |
-
Detailed performance and introduction are shown in our <a href="https://arxiv.org/abs/2410.09008"> 📑 Paper</a>.
|
| 24 |
-
|
| 25 |
<div align="left">
|
| 26 |
🚨 Unlike other LLMs, we incorporate LLMs with our pre-defined hierarchical thought template ([Buffer of Thought (BoT)](https://github.com/YangLing0818/buffer-of-thought-llm)) to conduct more deliberate reasoning than conventional CoT. It should be noted that our evaluation methods relies on pure mathematical reasoning abilities of LLMs, instead of leverage other programming methods such as PoT and ToRA.
|
| 27 |
</div>
|
|
|
|
| 20 |
|
| 21 |
Notably, our **SupperCorrect-7B** model significantly surpasses powerful **DeepSeekMath-7B by 7.8%/5.3% and Qwen2.5-Math-7B by 15.1%/6.3% on MATH/GSM8K benchmarks**, achieving new SOTA performance among all 7B models.
|
| 22 |
|
|
|
|
|
|
|
| 23 |
<div align="left">
|
| 24 |
🚨 Unlike other LLMs, we incorporate LLMs with our pre-defined hierarchical thought template ([Buffer of Thought (BoT)](https://github.com/YangLing0818/buffer-of-thought-llm)) to conduct more deliberate reasoning than conventional CoT. It should be noted that our evaluation methods relies on pure mathematical reasoning abilities of LLMs, instead of leverage other programming methods such as PoT and ToRA.
|
| 25 |
</div>
|