From fda1267d7d6600c04a6cd7eb2a818ebefb8999e4 Mon Sep 17 00:00:00 2001 From: Jonas Knobloch Date: Fri, 3 Apr 2026 19:20:57 +0200 Subject: Return document index in text iterator --- tokenizer/bpe/cmd/tokenize/main.go | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'tokenizer') 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 != "" { -- cgit v1.2.3