deepseek-ai / deepseek-ai/EPLB
how the weight initialize?
Open
- Dominant language
- Python
- Stars
- 1.4k
- Forks
- 210
- PR merge metrics
- No merged PRs in 30d
Description
Great work！
Can you give an example or explain how the weight is initialized? I guess it might be the number of tokens or flops? Does the number come from the training phase or the inference phase?
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.