summaryrefslogtreecommitdiff
path: root/llm/tokenizer.go
diff options
context:
space:
mode:
authorJonas Knobloch <jonas.knobloch@t-online.de>2025-11-13 23:04:57 +0100
committerJonas Knobloch <jonas.knobloch@t-online.de>2025-11-17 22:41:09 +0100
commit7073b124c5eb31169442ef18d1627b7ed7401280 (patch)
treef472b8a937fb5e2e3f235723cd5bafe422b3b647 /llm/tokenizer.go
parent019a25a6082a8cde372304e34dcd0ae3d5e875ed (diff)
Scaffold byte-pair correction
Diffstat (limited to 'llm/tokenizer.go')
-rw-r--r--llm/tokenizer.go5
1 files changed, 5 insertions, 0 deletions
diff --git a/llm/tokenizer.go b/llm/tokenizer.go
new file mode 100644
index 0000000..c6ea3c1
--- /dev/null
+++ b/llm/tokenizer.go
@@ -0,0 +1,5 @@
+package llm
+
+type Tokenizer interface {
+ Tokenize(s string) []int
+}