Hugging Face's logo
Reuben fernandes's picture
In a Training Loop šŸ”„
27 39 128

Reuben fernandes PRO

Reubencf
hugging-science
juiceb0xc0de's profile picture Zuiqiang's profile picture NickyNicky's profile picture
Ā·
http://reuben-fernandes.xyz/

AI & ML interests

LLM

Recent Activity

reacted to cesear64's post with šŸ§  1 day ago
Just published: how we built production Sango (Central African Republic) translation without fine-tuning, parallel corpus, or training compute. The method ā€” vocabulary-augmented prompting with a 581-entry native-speaker-verified lexicon ā€” generalizes to any of the ~2,000 African languages at the same data-poverty level. Recipe, dataset, and code template all included. šŸ“„ Blog: https://huggingface.co/blog/MEYNG/sangoai šŸ“¦ Dataset: https://huggingface.co/datasets/MEYNG/sango-vocabulary Would especially value feedback from anyone working on other low-resource African languages ā€” Ewondo, Lingala, Wolof next on our roadmap.
reacted to cesear64's post with šŸ‘€ 1 day ago
Just published: how we built production Sango (Central African Republic) translation without fine-tuning, parallel corpus, or training compute. The method ā€” vocabulary-augmented prompting with a 581-entry native-speaker-verified lexicon ā€” generalizes to any of the ~2,000 African languages at the same data-poverty level. Recipe, dataset, and code template all included. šŸ“„ Blog: https://huggingface.co/blog/MEYNG/sangoai šŸ“¦ Dataset: https://huggingface.co/datasets/MEYNG/sango-vocabulary Would especially value feedback from anyone working on other low-resource African languages ā€” Ewondo, Lingala, Wolof next on our roadmap.
reacted to cesear64's post with šŸ”„ 1 day ago
Just published: how we built production Sango (Central African Republic) translation without fine-tuning, parallel corpus, or training compute. The method ā€” vocabulary-augmented prompting with a 581-entry native-speaker-verified lexicon ā€” generalizes to any of the ~2,000 African languages at the same data-poverty level. Recipe, dataset, and code template all included. šŸ“„ Blog: https://huggingface.co/blog/MEYNG/sangoai šŸ“¦ Dataset: https://huggingface.co/datasets/MEYNG/sango-vocabulary Would especially value feedback from anyone working on other low-resource African languages ā€” Ewondo, Lingala, Wolof next on our roadmap.
View all activity

Organizations

MultišŸ¤–Transformers's profile picture Cohere Labs Community's profile picture Hugging Face Discord Community's profile picture LangGraph UserGroup's profile picture Konkani LLM's profile picture Hugging Science's profile picture MCP-1st-Birthday's profile picture Hugging Face Skills's profile picture 25daysofagents's profile picture ML intern explorers's profile picture Mistral Hack-a-ton 2026's profile picture SAFETY AYA's profile picture Reuben's Multimodal Data Lab's profile picture Build Small Hackathon's profile picture