AnswerDotAI / AnswerDotAI/ModernBERT
Yaml used to train the ModernBert
Open
- Dominant language
- Python
- Stars
- 1.7k
- Forks
- 145
- PR merge metrics
- No merged PRs in 30d
Description
Hi,
Thank you for the great work!
In the yamls/main I see multiple flex bert yamls. I am guessing the one used to train is: `yamls/main/flex-bert-rope-parallel-firstprenorm.yaml` and if not, is it possible to share the relevant yamls (basically just pointing out which yamls were used to train in the different training phases) used to train the model for reproducibility and further understand the different aspects of this repository?
Thanks
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.