mirror of
https://github.com/QwenLM/Qwen.git
synced 2026-05-20 16:35:47 +08:00
Update tech_memo.md
fix error link of GSM8k.
This commit is contained in:
@@ -146,7 +146,7 @@ We compared the code capabilities of pretrained models on [HumanEval](https://gi
|
||||
|
||||
#### Math
|
||||
|
||||
We compared the math capabilities of pretrained models on [GSM8K](https://github.com/openai/human-eval) (8-shot), and the results are as follows:
|
||||
We compared the math capabilities of pretrained models on [GSM8K](https://github.com/openai/grade-school-math) (8-shot), and the results are as follows:
|
||||
|
||||
| Model | Accuracy |
|
||||
| :----------- | -------: |
|
||||
|
||||
Reference in New Issue
Block a user