Skip to content

Commit

Permalink
Update main.py
Browse files Browse the repository at this point in the history
  • Loading branch information
dvsrepo authored Jul 9, 2024
1 parent 8243889 commit 8fd0619
Showing 1 changed file with 2 additions and 2 deletions.
4 changes: 2 additions & 2 deletions main.py
Original file line number Diff line number Diff line change
Expand Up @@ -33,13 +33,13 @@
hf_ds = hf_ds.remove_columns(["vectors"])

# Load existing hf dataset
previous_hf_ds = load_dataset(HF_DATASET_RESULTS, split="train")
previous_hf_ds = load_dataset(PARSED_RESULTS_DATASET, split="train")
print(f"Current HF dataset size: {len(previous_hf_ds)}")

# Add new submitted records
concatenated = concatenate_datasets([previous_hf_ds,hf_ds])
print(f"New HF dataset size: {len(concatenated)}")
concatenated.push_to_hub(HF_DATASET_RESULTS, private=True)
concatenated.push_to_hub(PARSED_RESULTS_DATASET, private=True)
print(f"New HF dataset size: {len(concatenated)}")

print(f"Deleting records")
Expand Down

0 comments on commit 8fd0619

Please sign in to comment.