53 lines
1.3 KiB
Markdown
53 lines
1.3 KiB
Markdown
|
---
|
|||
|
|
license: mit
|
|||
|
|
datasets:
|
|||
|
|
- xiaodongguaAIGC/step_sft
|
|||
|
|
language:
|
|||
|
|
- en
|
|||
|
|
pipeline_tag: text-generation
|
|||
|
|
library_name: transformers
|
|||
|
|
tags:
|
|||
|
|
- math
|
|||
|
|
- o1
|
|||
|
|
- reasoning
|
|||
|
|
- step
|
|||
|
|
- search
|
|||
|
|
base_model:
|
|||
|
|
- meta-llama/Llama-3.1-8B
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
|
|||
|
|
# 小冬瓜AIGC：Step-Wise数学推理
|
|||
|
|
|
|||
|
|
Test：[Colab](https://colab.research.google.com/drive/17-eEER7sV7xJ66pKiDIB9gEuS8phXeX3?usp=sharing)
|
|||
|
|
|
|||
|
|
## result
|
|||
|
|
|
|||
|
|
测试可以rejection sampling多次，以`\boxed{}`格式输出final asnwer
|
|||
|
|
|
|||
|
|
```python
|
|||
|
|
prompt = 'Tom has 12 apples. He gives 3 apples to each of his 4 friends. After that, he buys 10 more apples. How many apples does Tom have now?'
|
|||
|
|
step_generation(prompt, 128)
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
result
|
|||
|
|
|
|||
|
|
```text
|
|||
|
|
<|begin_of_text|>###System: You are MA-RLHF Chatbot, you should friendly answer the question
|
|||
|
|
###Question:Solve this math problem using step-by-step reasoning. Require that the output of each step ends with the " [SEP]
|
|||
|
|
" token.
|
|||
|
|
Tom has 12 apples. He gives 3 apples to each of his 4 friends. After that, he buys 10 more apples. How many apples does Tom have now?
|
|||
|
|
###Answer: At first, Tom has 12 apples. [SEP]
|
|||
|
|
He gives 3 apples to each of his 4 friends, so he gives him 4 * 3 = 12 apples. [SEP]
|
|||
|
|
After that, Tom has 12 - 12 = 0 apples left. [SEP]
|
|||
|
|
He buys 10 more apples, so he has 0 + 10 = 10 apples now. [SEP]
|
|||
|
|
Tom has 10 apples now. [SEP]
|
|||
|
|
Answer: 10 [SEP]
|
|||
|
|
I agree. [SEP]
|
|||
|
|
A possible answer.
|
|||
|
|
|
|||
|
|
# Answer
|
|||
|
|
|
|||
|
|
10 [SEP]
|
|||
|
|
<|end_of_text|>
|
|||
|
|
```
|