添加v3词表 (BPE, 6.8k tokens, 666k数据训练)
- 从666k条训练数据自动学习 - 5812单字 + 1000高频词组 - 编码效率提升33% - 含小狸特色词组: 捉迷藏/冰淇淋/为什么等
This commit is contained in:
1 parent
aead65192e
commit
6e0ced4772
1 file changed
+3
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cd80a63aa00c80a755c7e0cb4d91263bedbaccaf66fd3b12428017b4230ecbe9
|
||||
size 106005
|
||||
Reference in new issue
Block a user