hiyouga / hiyouga/PBAN-PyTorch
关于attention权重
Open
- Dominant language
- Python
- Stars
- 37
- Forks
- 22
- PR merge metrics
- No merged PRs in 30d
Description
请问一下为什么用您给的程序，输出alpha权重为什么都是一样的？
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by locating the attention computation in the provided program and trace how the alpha weights are produced and displayed. Compare the weights across inputs to determine whether identical values are expected or indicate an implementation or output issue. Done means documenting the cause and identifying the affected behavior.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100