YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)
Agreement reporting (HITL vs AI suggestion) After reviewing the 100 high-risk patent claims, we created a final human label (is_green_gold). We then measured agreement as the percentage of cases where the AI suggestion exactly matched the human gold label (N = 100). The Assignment 2 simple LLM labels matched the human gold label in 94% of cases, and the Assignment 3 Agentic System labels also matched the human gold label in 94% of cases.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support