Nicole comments

Repositories
Issues
Comments

Results 4 comments of


                                            Nicole

How can i run a pretrained model for prediction on new data?

where did you get the 30k-clean.model ?

Validation perplexity is 146.71 at the end of training (24 epochs)

I ran the code yesterday and received a result of 156.097 averaged validation PPL, 149.565 averaged test PPL. So I am reading your code and the original.The first different thing...

questions about the padding value

Yes, pad_token_id should be 0

Ziya-Reader-13B-v1.0长度限制4-8K，请问LongBench中文多文档QA问题都是8K-27K，是如何测评的，采用首尾截断，还是重新构造了数据集？

@Johnny-xyz 你好，ziya-reader的长度限制是8k，采用后向截断，只保留前面的context