summaryrefslogtreecommitdiff
path: root/tokenizer
diff options
context:
space:
mode:
authorJonas Knobloch <jonas.knobloch@t-online.de>2026-04-03 19:20:57 +0200
committerJonas Knobloch <jonas.knobloch@t-online.de>2026-04-03 20:06:42 +0200
commitfda1267d7d6600c04a6cd7eb2a818ebefb8999e4 (patch)
treecbfab8e35e396a8b5dc4e9d5ed765ad699dac1db /tokenizer
parentc1644da32ecb9856f15e2c919a84d2666d5ef29c (diff)
Return document index in text iterator
Diffstat (limited to 'tokenizer')
-rw-r--r--tokenizer/bpe/cmd/tokenize/main.go6
1 files changed, 1 insertions, 5 deletions
diff --git a/tokenizer/bpe/cmd/tokenize/main.go b/tokenizer/bpe/cmd/tokenize/main.go
index a0519cf..08d88aa 100644
--- a/tokenizer/bpe/cmd/tokenize/main.go
+++ b/tokenizer/bpe/cmd/tokenize/main.go
@@ -53,9 +53,7 @@ func main() {
defer pb.Close()
- n := 0
-
- for d := range reader.Texts() {
+ for n, d := range reader.Texts() {
if n >= 1000 {
break
}
@@ -65,8 +63,6 @@ func main() {
_ = tokens
processed.Add(1)
-
- n++
}
if *memprofile != "" {