datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
hci_random_food_10k_jsonhci_group_food_9khci_oneCol_1205hci_food_30ksmoILM2-360M_HCI_blindspot
Dataset: SmolLM2-360M UX/HCI Blind Spots
Model Tested: HuggingFaceTB/SmolLM2-360M
Task: Identify failure modes in small-parameter frontier models when handling niche technical constraints in UI/UX, Web Performance, and Human-Computer Interaction.
Dataset Overview
This dataset contains 20 high-fidelity "Blind Spots" where SmolLM2-360M failed to provide technically accurate or logically sound responses. The failures range from Degenerative Repetition to Hallucinated… See the full description on the dataset page: https://huggingface.co/datasets/abdulsamad-111/smoILM2-360M_HCI_blindspot.