Skip to content

Commit 6c7d0d2

Browse files
authored
fix cache miss problem (#22)
1 parent fa7f2a1 commit 6c7d0d2

File tree

3 files changed

+4
-3
lines changed

3 files changed

+4
-3
lines changed

tokenizer_ts/package-lock.json

Lines changed: 2 additions & 2 deletions
Some generated files are not rendered by default. Learn more about customizing how changed files appear on GitHub.

tokenizer_ts/package.json

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -2,7 +2,7 @@
22
"name": "@microsoft/tiktokenizer",
33
"displayName": "tiktokenizer",
44
"description": "Tokenizer for OpenAI large language models.",
5-
"version": "1.0.1",
5+
"version": "1.0.2",
66
"author": {
77
"name": "Microsoft Corporation"
88
},

tokenizer_ts/src/tikTokenizer.ts

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -213,6 +213,7 @@ export class TikTokenizer {
213213
const token = this.encoder?.get(uint8ArrayToString(bytes));
214214
if (token !== undefined) {
215215
tokenIds.push(token);
216+
this.cache.set(match[0], [token]);
216217
} else {
217218
const encodedTokens = bytePairEncode(bytes, this.encoder!);
218219
tokenIds.push(...encodedTokens);

0 commit comments

Comments
 (0)