Skup podataka sa Hugging Face · libredb

Database agent runs: 8,199 tool-calling runs across 40 language models

Licenca
MITdozvoljena komercijalna upotrebaTekst licence
Licenca dozvoljava komercijalnu upotrebu. Obično treba navesti autora — tačni uslovi su u tekstu licence.
Formati
JSON, JSONL, PY, TXT
Veličina
78 MB
Ažurirano
21. 9. 2026.

Opis

LibreDB Agent Benchmark 8,199 agent runs · 39 open-weight models served locally, plus one hosted model as a control · 6 task surfaces · 110,711 ledger events · 14,008 refused tool calls This is the complete measurement record behind the paper What Stops a Small Language Model From Driving a Database Agent. It is not a scored summary: it is every event the server wrote while the runs happened, released so that every number in the paper can be recomputed, and disagreed with…

Opis sa Hugging Face, skraćen.

Fajlovi (8)

  • JSONLevents.jsonl69 MB
  • PYhf-export.py12 kB
  • TXTleaderboard-pooled.txt2,5 kB
  • TXTleaderboard-row.txt2,4 kB
  • JSONLrefusals.jsonl4,4 MB
  • JSONLruns.jsonl4,6 MB
  • PYscore.py8,5 kB
  • PYverify.py7,7 kB

DataHunter ne čuva i ne deli ove fajlove: svaki link vodi do izvornog sajta. Pre upotrebe tamo proverite licencu.

Pronađi druge skupove