# hon9kon9ize Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/hon9kon9ize
> Markdown URL: https://aitinkerers.org/technologies/hon9kon9ize.md
> Technology record last updated: 2026-02-26T14:49:10Z
> Generated: 2026-09-20T14:40:58Z

Hon9kon9ize is the AI research collective engineering large language models and critical datasets to secure Cantonese and Hong Kong culture against digital marginalization.

Hon9kon9ize actively develops AI resources for Cantonese: a language often sidelined as “low-resource” by global LLMs. The organization counters this gap by creating crucial open-source assets, including over 23 datasets and specialized models like CantoneseLLMChat-v1.0 (up to 72B parameters). Their work also established HKCanto-Eval, the world's first AI evaluation benchmark specifically assessing large language models' understanding of Cantonese linguistics and Hong Kong cultural context. This focused engineering ensures the digital preservation and accessibility of Cantonese for its 85 million-plus speakers.

- Official technology site: https://www.hon9kon9ize.com
- Public AI Tinkerers demos and talks: 1
- Result page: 1 of 1

## Recent Public Talks and Demos

### [CantoneseLLM](https://hong-kong.aitinkerers.org/talks/rsvp_rniZKOvRbBA)

This talk addresses the critical challenge faced by leading Large Language Models (LLMs) when processing the highly dynamic, slang-infused, and diverse linguistic landscape of Hong Kong Cantonese. Despite being a highly utilized language, Cantonese remains a "low-resource" language in the global AI training ecosystem, leading to significant failure and reduced performance for general-purpose LLMs (like those from major tech companies). We will present **CantoneseLLM**, an LLM developed by **Votee** specifically trained to tackle this complexity. CantoneseLLM is designed to handle the massive target distribution increase caused by intense Cantonese slang input, which typically causes external models to fail. The presentation will cover: 1. **The Cantonese Data Crisis:** Why traditional LLM training fails when faced with localized Hong Kong language nuances. 2. **Community Empowerment:** The role of the **"hon9kon0ize"** community (a dedicated Cantonese AI group) in curating and pushing forward high-quality, local datasets necessary for training specialized models. 3. **The Specialized Solution:** An in-depth look at **Votee's CantoneseLLM**—how it was built, its unique training methodologies for low-resource languages, and its performance benchmarks. 4. **Comparative Analysis with the "HK Canto Eval" Benchmark:** To measure what truly matters, the **hon9kon9ize** community and **Votee** co-developed the **"HK Canto Eval"** benchmark. We will first present how leading SOTA models like Ernie 4.5 perform on this culturally-specific suite. We then demonstrate how **CantoneseLLM** achieves highly comparable results on these demanding local tasks, proving a specialized model can match global giants when tested on true linguistic and cultural fluency. This session serves as a crucial case study, showcasing how dedicated, localized effort can successfully tackle the low-resource language problem and boost the Cantonese AI community.

- Event context: AI Tinkerers - Hong Kong Meetup (August) - Meetup with Baidu PaddlePaddle — 2025-08-22 — Hong Kong
- Public talk page: https://hong-kong.aitinkerers.org/talks/rsvp_rniZKOvRbBA

## Related Technologies

- [Baidu Ernie 4](https://aitinkerers.org/technologies/baidu-ernie-4) ([Markdown](https://aitinkerers.org/technologies/baidu-ernie-4.md)) — 1 public demo
- [CantoneseLLM](https://aitinkerers.org/technologies/cantonesellm) ([Markdown](https://aitinkerers.org/technologies/cantonesellm.md)) — 1 public demo
- [Hugging Face](https://aitinkerers.org/technologies/hugging-face) ([Markdown](https://aitinkerers.org/technologies/hugging-face.md)) — 41 public demos
- [Web scraping](https://aitinkerers.org/technologies/web-scraping) ([Markdown](https://aitinkerers.org/technologies/web-scraping.md)) — 9 public demos