# Researchers release Pearl-Chat, a Luganda language model with 8.5M parameters

Digest AI · Generative AI & Models · published 2026-10-19T04:00:00Z

Canonical: https://digestai.news/story/researchers-release-pearl-chat-a-luganda-language-model-with-8-5m-para

## Summary

A team of researchers introduced Pearl-Chat, an 8,473,122‑parameter causal decoder‑only transformer built for Luganda, a Bantu language spoken by over 10 million people. The model was engineered from first principles in JAX and Flax NNX, using explicit functional state decomposition and deterministic resumable data streaming via Google Grain.

Training proceeded in two stages: pre‑training on 59,501 sequences from diverse corpora, followed by instruction fine‑tuning on 510 dialogues. Over 4,000 optimization steps the validation cross‑entropy loss fell from 9.4695 (perplexity: 12,958.98) to 0.1818 (perplexity: 1.20). On a held‑out benchmark Pearl-Chat achieved 0.9792 ROUGE‑L and 0.9405 BLEU. The authors released a Python Server‑Sent Events streaming runtime and open‑sourced all weights, tokenizers, and code.

## Key points

- Pearl-Chat has 8,473,122 parameters and a 8,192‑token BPE tokenizer with 1.60 tokens per word fertility.
- Training used 59,501 pre‑training sequences and 510 fine‑tuning dialogues across 4,000 steps.
- Benchmark scores: 0.9792 ROUGE‑L and 0.9405 BLEU on a three‑tier diagnostic set.

## Why it matters

Provides a high‑quality, open‑source language model for Luganda, reducing the AI gap for low‑resource African languages and enabling local applications.

## Sources

1. [Pearl-Chat: Engineering a native Luganda language model from first principles in JAX and Flax NNX](https://arxiv.org/abs/2610.22529) (arXiv cs.CL, 2026-10-19, primary source)

## Cite

Digest AI, "Researchers release Pearl-Chat, a Luganda language model with 8.5M parameters", 19 October 2026, https://digestai.news/story/researchers-release-pearl-chat-a-luganda-language-model-with-8-5m-para

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/researchers-release-pearl-chat-a-luganda-language-model-with-8-5m-para.json