mirror of
https://github.com/SakanaAI/doc-to-lora.git
synced 2026-05-05 13:02:38 +02:00
Doc-to-LoRA release
This commit is contained in:
commit
1abe8ae16d
92 changed files with 22131 additions and 0 deletions
10
data/download_fineweb_edu.py
Normal file
10
data/download_fineweb_edu.py
Normal file
|
|
@ -0,0 +1,10 @@
|
|||
from huggingface_hub import snapshot_download
|
||||
|
||||
if __name__ == "__main__":
|
||||
fw_dir = "./data/raw_datasets/fineweb_edu/"
|
||||
snapshot_download(
|
||||
"HuggingFaceFW/fineweb-edu",
|
||||
repo_type="dataset",
|
||||
local_dir=fw_dir,
|
||||
allow_patterns="sample/100BT/*",
|
||||
)
|
||||
Loading…
Add table
Add a link
Reference in a new issue