↓Skip to main content

Cogito Capability Checks

Cogito Capability Checks: Long-Context Datasets for Small Models

·2341 words·11 mins
Five open Hugging Face datasets that test whether small (5M–100M) models actually use facts from far back in their context: recall, binding, structure, multi-hop, counting and deduction, on a length ladder from 1k to 128k tokens.