InkubaLM-0.4B: A Small Language Model for African Languages
A 0.4B-parameter transformer language model trained on African languages by Lelapa AI, released with associated research (arXiv:2408.17024).
Search titles, authors, subjects and dates from across the DARE African Knowledge Repository.
27 resources found in the repository.
A 0.4B-parameter transformer language model trained on African languages by Lelapa AI, released with associated research (arXiv:2408.17024).
Evaluation set of GSM8K translations into 16 African languages with 250 test problems per language for multilingual mathematical reasoning.
Largest publicly available topic-classification dataset based on Flores-200, covering 205 languages and dialects with a compact seven-class label set.
Bilingual practical notebooks from Indaba 2024 covering JAX, probabilistic programming, GNNs, responsible AI, LLMs, diffusion models, federated learning, low-resource NLP and recommender systems.
Parallel English-Shona sentences derived from OPUS MT560 for machine translation, cross-lingual NLP and language-model fine-tuning.
Audio-transcription parallel data for chiShona tagged for translation, conversational, token-classification and text-generation tasks.
Human-annotated multilingual instruction-tuning dataset curated via an open-science annotation programme with substantial African-language participation.
Large multilingual instruction dataset collection assembled for the Aya project, aggregating open datasets across 101 languages.
High-quality professionally translated Amharic Wikipedia articles released by Addis AI for Amharic language-model and NLP work.
Community-maintained successor to FLORES-200 for multilingual MT evaluation with expanded language coverage.
An open-access volume on the intersection of large language models and cybersecurity, examining emerging threats, exposure and data leakage, adversarial uses, and practical mitigation strategies for LLM-enabled systems.
An introduction to the safety, ethics and societal implications of artificial intelligence, covering technical safety problems, misuse and robustness, fairness, privacy, governance, economic impacts and the future of AI systems.