diff options
Diffstat (limited to 'tokenizer/bpe/special.go')
| -rw-r--r-- | tokenizer/bpe/special.go | 18 |
1 files changed, 18 insertions, 0 deletions
diff --git a/tokenizer/bpe/special.go b/tokenizer/bpe/special.go new file mode 100644 index 0000000..405199f --- /dev/null +++ b/tokenizer/bpe/special.go @@ -0,0 +1,18 @@ +package bpe + +// Add helper to ensure special token +// wip-special-tokens + +func EnsureSpecialToken(t *Tokenizer, token string) int { + vocab := Vocab(t) + + for i, v := range vocab { + if v == token { + return i + } + } + + AddToken(t, token) + + return len(vocab) - 1 +} |
