summaryrefslogtreecommitdiff
path: root/llmc/cmd/data/fineweb.go
diff options
context:
space:
mode:
authorJonas Knobloch <jonas.knobloch@t-online.de>2026-04-30 13:10:03 +0200
committerJonas Knobloch <jonas.knobloch@t-online.de>2026-04-30 13:19:08 +0200
commit806dcb7f2c01514275dab76116d494345ffb0fd0 (patch)
treed436e8ca6fd71942d72d37d403f78b7abdf52a1b /llmc/cmd/data/fineweb.go
parent4740e5aa19012e5f8e67ac8cb857d9741208c364 (diff)
Return number of written shards
Diffstat (limited to 'llmc/cmd/data/fineweb.go')
-rw-r--r--llmc/cmd/data/fineweb.go2
1 files changed, 1 insertions, 1 deletions
diff --git a/llmc/cmd/data/fineweb.go b/llmc/cmd/data/fineweb.go
index a1bf7df..599089d 100644
--- a/llmc/cmd/data/fineweb.go
+++ b/llmc/cmd/data/fineweb.go
@@ -37,7 +37,7 @@ func fineWeb() {
docs := llmc.TokenizeAll(reader, tokenizer, 50256)
- if err := llmc.WriteShards(shelf.Abs("llmc/edu_fineweb100B"), "edu_fineweb", 100_000_000, docs); err != nil {
+ if _, err := llmc.WriteShards(shelf.Abs("llmc/edu_fineweb100B"), "edu_fineweb", 100_000_000, docs); err != nil {
log.Fatal(err)
}