Stanisław Szymczyk
sszymczyk
AI & ML interests
None yet
Organizations
None yet
sszymczyk's activity
Calculation of _mscale during YARN RoPE scaling
#4 opened 3 days ago
by
sszymczyk
Wrong BOS and EOS tokens in tokenizer.model file
1
#12 opened 22 days ago
by
sszymczyk
Confusing ArcticDecoderLayer::forward() implementation
#11 opened 23 days ago
by
sszymczyk
Problem with repeated generation of newline characters
2
#3 opened 24 days ago
by
sszymczyk
Possible error in tokenizer.json
6
#6 opened about 1 month ago
by
sszymczyk
Model is paraphrasing text instead of citing it verbatim
3
#7 opened about 1 month ago
by
sszymczyk