pkoukk / tiktoken-go

go version of tiktoken
MIT License
601 stars 67 forks source link

应当使用 allowedSpecial 以代替 disallowedSpecial?? #7

Closed xgfone closed 1 year ago

xgfone commented 1 year ago
// func (t *Tiktoken) Encode(text string, allowedSpecial []string, disallowedSpecial []string) []int {
    var allowedSpecialSet map[string]any
    if len(allowedSpecial) == 0 {
        allowedSpecialSet = map[string]any{}
    } else if len(disallowedSpecial) == 1 && disallowedSpecial[0] == "all" {
        allowedSpecialSet = t.specialTokensSet
    } else {
        allowedSpecialSet = map[string]any{}
        for _, v := range allowedSpecial {
            allowedSpecialSet[v] = nil
        }
    }

@pkoukk 暂时没有看全部代码的逻辑,但感觉 disallowedSpecial 怪怪,不知道是否应该是 allowedSpecial

pkoukk commented 1 year ago

这里确实有问题,我会尽快修复

xgfone commented 1 year ago

@pkoukk 有计划发布 v0.1.1 or v0.2.0 版本吗?