v2: 2M training, dropout 0.1, full-corpus tokenizer — chrF 51.65 case-normalized (was 45.62) 472017b verified AstralPotato commited on 5 days ago
v2: 2M training, dropout 0.1, full-corpus tokenizer — chrF 48.93 (was 45.62) d7fa769 verified AstralPotato commited on 5 days ago
Upload en-ms Transformer (6+2 Tied, 16K BPE, chrF 45.62) e7f17a4 verified AstralPotato commited on 7 days ago