We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent cc5e930 commit a81fbfcCopy full SHA for a81fbfc
src/dataset/load.py
@@ -35,7 +35,7 @@
35
# load_dataset("cerebras/SlimPajama-627B", trust_remote_code=True)
36
# TinyLlamaが使ってる、311 GB
37
# load_dataset("bigcode/starcoderdata", trust_remote_code=True)
38
-# 825 GB
+# 886 GB
39
# load_dataset("EleutherAI/pile", "all", trust_remote_code=True)
40
# load_dataset("oscar")
41
0 commit comments