Spaces:
Running
Running
File size: 3,654 Bytes
b485a88 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 | """ModelBrew Dataset Cleaner — Hugging Face Space.
Upload a fine-tuning dataset (.jsonl/.json/.csv), get a scored issue report
and a cleaned export with critical rows dropped.
"""
import tempfile
from pathlib import Path
import gradio as gr
import pandas as pd
from modelbrew_cleaner import Severity, clean_file, export_clean, issue_summary
MAX_ROWS = 5000
SAMPLE = Path(__file__).parent / "sample.jsonl"
SEV_ORDER = {"critical": 0, "warning": 1, "suggestion": 2}
def analyze(path: str):
rows = clean_file(path)
if len(rows) > MAX_ROWS:
raise gr.Error(
f"This demo caps at {MAX_ROWS:,} rows (got {len(rows):,}). "
f"Run locally with `pip install modelbrew-cleaner` for unlimited size."
)
records = [
{
"row": r.row_index,
"severity": i.severity.value,
"check": i.code,
"message": i.message,
"auto-fixable": bool(i.auto_fixable),
}
for r in rows
for i in r.issues
]
records.sort(key=lambda x: (SEV_ORDER.get(x["severity"], 9), x["row"]))
df = pd.DataFrame(records, columns=["row", "severity", "check", "message", "auto-fixable"])
s = issue_summary(rows)
n_critical_rows = sum(
1 for r in rows if any(i.severity == Severity.critical for i in r.issues)
)
summary_md = (
f"### {len(rows):,} rows scanned\n"
f"- 🔴 **{s['critical']} critical** issues ({n_critical_rows} rows dropped in the cleaned export)\n"
f"- 🟡 **{s['warning']} warnings**\n"
f"- 🔵 **{s['suggestion']} suggestions**\n"
)
cleaned = export_clean(rows)
out = tempfile.NamedTemporaryFile(
mode="w", suffix=".cleaned.jsonl", delete=False, encoding="utf-8"
)
out.write(cleaned)
out.close()
return summary_md, df, out.name
def analyze_upload(file):
if file is None:
raise gr.Error("Upload a .jsonl, .json, or .csv file — or click 'Try the sample'.")
return analyze(file.name if hasattr(file, "name") else str(file))
def analyze_sample():
return analyze(str(SAMPLE))
with gr.Blocks(title="ModelBrew Dataset Cleaner") as demo:
gr.Markdown(
"# 🧹 ModelBrew Dataset Cleaner\n"
"90+ quality checks for fine-tuning datasets: PII with checksum validation, "
"exact/near duplicates, prompt-injection & jailbreak patterns, label errors, "
"truncated responses, and more. Critical rows are dropped from the cleaned export.\n\n"
"`pip install modelbrew-cleaner` to run locally on datasets of any size."
)
with gr.Row():
upload = gr.File(label="Dataset (.jsonl / .json / .csv)", file_types=[".jsonl", ".json", ".csv"])
with gr.Row():
run_btn = gr.Button("Clean my dataset", variant="primary")
sample_btn = gr.Button("Try the sample (deliberately dirty)")
summary = gr.Markdown()
issues = gr.Dataframe(label="Issues found", interactive=False, wrap=True)
cleaned_file = gr.File(label="Cleaned dataset (critical rows dropped)")
run_btn.click(analyze_upload, inputs=upload, outputs=[summary, issues, cleaned_file])
sample_btn.click(analyze_sample, inputs=None, outputs=[summary, issues, cleaned_file])
gr.Markdown(
"---\n"
"Built by [ModelBrew](https://modelbrew.ai) — we work on fine-tuning without "
"catastrophic forgetting (patent-pending CRMA adapters), and honest measurement "
"starts with clean data. Read: *Your forgetting benchmark is lying to you* "
"({{HF_ARTICLE_URL}}) · [pip package]({{PYPI_URL}})"
)
if __name__ == "__main__":
demo.launch()
|