Weikuan Wang issues

Repositories
Issues
Comments

Results 2 issues of


                                            Weikuan Wang

found a small typo in the run command 'python run.py ---train=True --dataset=NYT'

---train=True should be --train=True ?

Evaluate on long context (32k,64k etc..) on 30B/70B large models

Hi, I found that the original script cannot handle large models on long context effectively, since it use multiprocess to load an entire model on a single gpu. I also...