
Lightweight cross-encoders that re-order retrieved passages by true relevance. From a 22.7M-parameter micro-reranker to a 150M ModernBERT model, built for fast CPU-friendly inference.


MIST RerankCross-encoder reranker (22.7M-parameter micro) that re-orders retrieved passages by true relevance for search and RAG.

MIST RerankCross-encoder reranker (150M-parameter ModernBERT) that re-orders retrieved passages by true relevance for search and RAG.
More of the stack, organised the same way.

Frontier-merged LLMs: from MIST-Mini-8B to MIST-1-140B, including reasoning-tuned Thinking variants.

Language identification: from 5 Nigerian languages to 25 languages worldwide.

Diacritic & tone restoration for YorĂčbĂĄ, Igbo, Hausa and beyond.