New discussion

Dataset used to train SantaCoder

#43 opened 10 months ago by nihaljn

Question about model architecture

1
#40 opened about 1 year ago by sh0416

Stopping criteria

#39 opened about 1 year ago by Mariusbrm

How to reproduce Table 7?

#36 opened about 1 year ago by sh0416

how to download fim benchmark data?

#33 opened about 1 year ago by zxyscz

Question: MHA to MQA Conversion

#27 opened over 1 year ago by kirazT

num_return_sequences and num_beams > 1

1
#17 opened over 1 year ago by tlphams