Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions .pre-commit-config.yaml
Original file line number Diff line number Diff line change
@@ -1,6 +1,8 @@
---
ci:
autoupdate_schedule: quarterly
autofix_prs: false
submodules: false

repos:
- repo: https://github.com/pre-commit/pre-commit-hooks
Expand Down
2 changes: 1 addition & 1 deletion experiments/data/prepare_chemrxiv.py
Original file line number Diff line number Diff line change
Expand Up @@ -39,5 +39,5 @@
# execute gpt-neox processing
gpt_tool_path = f"{args.gptneox_dir}/tools/preprocess_data.py"
os.system(
f"python {gpt_tool_path} --input {data_path} --output-prefix {save_path}/data --vocab /fsx/pile/20B_tokenizer.json --dataset-impl mmap --tokenizer-type HFTokenizer --append-eod"
f"python {gpt_tool_path} --input {data_path} --output-prefix {save_path}/data --vocab /fsx/pile/20B_tokenizer.json --dataset-impl mmap --tokenizer-type HFTokenizer --append-eod" # noqa: E501
)