Issues
- 0
When Support Unigram?
#44 opened by Doloxetine - 1
regexp dont support ?i
#43 opened by xuxiaoxia96 - 0
- 2
remove log from init
#39 opened by jackielii - 0
- 2
please fix this bug: int overflow
#36 opened by HgLiJiahao - 1
Compile to wasm target
#35 opened by tiero - 0
OpenAI CLIP tokenization support?
#34 opened by kristofmaar - 2
panic:fatal error: concurrent map writes
#32 opened by ZeroYuJie - 6
panic: assignment to entry in nil map
#31 opened by AlamoTNT - 2
Missing roberta-base-vocab.json
#26 opened by johntrob14 - 2
BOS/EOS tokens
#17 opened by trpstra - 1
Bump version?
#18 opened by hugbubby - 4
How to load self-made vocab.txt
#24 opened by lierik - 3
Performance / Parallelization Support
#20 opened by JoeREISys - 2
- 0
- 0
Truncation and Padding not working properly
#14 opened by sugarme - 1
Wordpiece Decoder
#13 opened by sugarme - 0
Decoder using pointer to interface
#12 opened by sugarme - 0
Add optional `addSpecialTokens` when encoding
#11 opened by sugarme - 0
pretrained tokenizers
#9 opened by sugarme - 1
- 0
- 0
pointer receiver
#4 opened by sugarme - 0
serialization
#2 opened by sugarme