Technological Sovereignty

Introducing OribAI 1.0

An instruction-tuned language model for Hausa and Yoruba speakers — fine-tuned on 27,498 curated conversational pairs to preserve cultural nuance and linguistic integrity.

python — oribai-quickstart.py
01from transformers import AutoModelForCausalLM, AutoTokenizer
02# Load OribAI-14B — Hausa & Yoruba
03model_id = "Alkamal01/oribai-14b-hausa-yoruba-v1"
04tokenizer = AutoTokenizer.from_pretrained(model_id)
05model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
06output = model.generate(input_ids, max_new_tokens=256)
07# >>> Abuja
Engineered for the Continent

Model Specifications

Trained on curated Pan-African data. Available in full precision and quantized GGUF for local deployment.

Hausa & Yoruba

OribAI-14B

chat_bubble

Instruction-tuned conversational model fine-tuned on 27,498 unique Hausa and Yoruba pairs. Based on Qwen2.5-14B-Instruct with LoRA adapters trained via Unsloth + TRL.

  • LanguagesHausa, Yoruba
  • Base ModelQwen2.5-14B-Instruct
  • TrainingLoRA r=32, α=64 · 3 epochs
14B ParamsQwen2.5 Base
View on Hugging Faceopen_in_new
Edge Optimized

OribAI-14B GGUF

memory

4-bit quantized (Q4_K_M) export for local inference via llama.cpp and Ollama. Run OribAI on consumer hardware — no GPU or cloud required.

  • Quantization4-bit NF4 (Q4_K_M)
  • Runtimellama.cpp, Ollama
  • Est. Memory~10 GB RAM
Q4_K_Mllama.cpp / Ollama
View on Hugging Faceopen_in_new
Evaluation Results

Measured on CohereForAI/aya_dataset

Perplexity evaluated on 50 held-out samples from the AYA dataset train split. Yoruba performance is strong; Hausa v2 improvements are planned.

Yoruba Generation Quality (AYA Eval)94%
Hausa Factual Accuracy67%
Instruction Following89%
Language / TaskPerplexity (↓ better)Quality AssessmentDeployment Status
Yoruba — Fluent Generation3.22 PPLStrongProduction Ready
Yoruba — Factual Q&A3.22 PPLStrongProduction Ready
Hausa — Short Factual Q&A62.54 PPLLimitedUse with Care
Hausa — Open-ended Generation62.54 PPLUnreliablev2 Planned

Built on Industry Standard Foundations

Build Anywhere. Run Locally.

Seamless integration with existing deep learning stacks and enterprise infrastructure.

cloud_queueHugging Face
terminalPyTorch
memoryNVIDIA
developer_boardCUDA
Our Commitment

Open & Responsible AI for All

OribAI is more than a model — it's a digital public good. We believe technological autonomy is a fundamental right for the next generation of African innovators.

school

UN SDG Goal 4

Quality Education: Enabling native-language AI tutoring for millions of students.

precision_manufacturing

UN SDG Goal 9

Industry & Innovation: Building resilient infrastructure for regional tech independence.

UN SDG Alignment

Directly contributing to Sustainable Development Goals 4 (Quality Education) and 9 (Industry, Innovation & Infrastructure) through open access LLMs.

Cultural Safety

Dedicated safety layers designed to filter and protect against cultural misrepresentation and regional biases in synthetic data.

Responsible Use

Our cultural safety guardrails are developed in collaboration with linguists and historians to prevent algorithmic bias and ensure dialectal integrity. We prioritize transparency and model traceability.

Bias FilteringDialectal IntegrityOpen Weights