ByteDance-Seed / ByteDance-Seed/decoupleQ
关于decoupleQ文献所述的结果异常
Open
- Dominant language
- Cuda
- Stars
- 153
- Forks
- 10
- PR merge metrics
- No merged PRs in 30d
Description
decoupleQ团队你好，
看了decoupleQ的文章，有个问题想问一下。我注意到文章中提到实验测试部分的Table 2中，W2A16的decoupleQ对应于2-13B的PPL (13.03) 比2-7B (9.74) 的PPL大，具有更多参数的模型PPL反而增加了，有点儿反直觉，这个后来有进一步的解释或进展吗？
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by reading the referenced article and Table 2, focusing on the W2A16 results for the 2-7B and 2-13B models. Investigate whether the reported PPL values are reproducible and whether the paper or repository contains an explanation. Done means documenting a supported explanation or confirming the result as an unresolved issue.
Written by the indexing model from the issue text.
Assessment
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100