Update src/dataset/load.py

yuiseki · Mar 28, 2024 · a81fbfc · a81fbfc
1 parent cc5e930
commit a81fbfc
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/src/dataset/load.py b/src/dataset/load.py
@@ -35,7 +35,7 @@
 # load_dataset("cerebras/SlimPajama-627B", trust_remote_code=True)
 # TinyLlamaが使ってる、311 GB
 # load_dataset("bigcode/starcoderdata", trust_remote_code=True)
-# 825 GB
+# 886 GB
 # load_dataset("EleutherAI/pile", "all", trust_remote_code=True)
 # load_dataset("oscar")