Spaces:

---

stacklok

/

llm_security_leaderboard

like 0

Running

• Add README describing local setup
• Create local setup that does not rely on HF requests and results datasets
• Fix queue UI reload
• Fix reading sub-directories

TODO:

• The logic to pull off the queue and evaluate the model still needs to be written

Current state:

• A model can be submitted and after 2 minutes will appear in the pending evaluation queue

👀