AI research programme · not a public product
Omnis AI

Our AI model and intelligence initiative.

Omnis is AfriStack's long-term AI development programme, covering model training, adaptation, AI agents, inference, orchestration, evaluation and intelligent infrastructure.

We have already trained and tested our own models. This page is the honest record of what they achieved, what they cannot do, and where they go next.

AfriStack Smart System Ltd
AfriStack AI platform & ecosystem
Omnis — model family
Omnis Tiny
Trained from scratch
Omnis Base
Adapted open-weight
Omnis Gateway
Routing & orchestration
Omnis Tiny

A language model trained from scratch.

A compact, decoder-only language model built to validate our end-to-end model development pipeline. No pretrained weights. No external inference API. The tokenizer, the architecture, the training loop and the data pipeline are ours.

Pretraining

15,000 steps · 983M tokens · ~12 hours on one 6 GB consumer laptop GPU

MetricStep 500Final
Held-out perplexity237.541.2
Validation loss5.47003.7179
Next-token top-119.9%34.5%
Next-token top-536.9%55.9%
Factual continuation, top-100%75%
Median fact rank2097

Instruction tuning

504 steps · 63,000 conversations · 8.4M tokens · ~15 minutes

After instruction tuning, the model answers rather than continuing text, and holds its own identity — final validation loss 1.6479, down from a 3.7179 base.

U: who are you? A: I am Omnis, AfriStack's AI assistant. U: who made you? A: I was created by AfriStack — AfriStack Smart System Ltd.

Identity holding is the point of a proprietary identity set. Without one, a model trained on web text claims to be somebody else's assistant.

What it cannot do — stated plainly

A model at this scale is not a product, and we do not present it as one. It is a learning vehicle that proves the pipeline, the tokenizer and the training stack work end to end. Anyone who tells you a model this size can power a consumer assistant is selling something.

Repetition loops

Some prompts fall into repetition. Mitigated at inference with a repetition penalty, and expected to improve with more data rather than more steps.

Train/validation gap

A +0.68 gap indicates we reached the useful ceiling for this parameter count on this corpus. More permissive data is already queued for the next dataset revision.

Thin world knowledge

The corpus is educational and mathematical, so literature and science land better than geography. Answer format is correct; answer content is often wrong at this size.

Architecture

A decoder-only transformer using modern-standard components, chosen for stability and efficiency rather than novelty.

  • RMSNorm pre-normalisation — cheaper and more stable than LayerNorm
  • RoPE rotary position embeddings — extrapolates better than learned positions
  • SwiGLU feed-forward — stronger than a ReLU or GELU MLP at equal parameter count
  • Tied embeddings — input embedding doubles as output projection
  • Flash attention and no biases in linear layers

Presets

PresetLayersHeadsd_modelContextParams
Omnis Tiny 0.188512512~42M
Omnis Tiny 0.212127681024~110M
Omnis Small 1.0241610242048~340M

Every artefact is versioned and reproducible: the model, the tokenizer, the dataset and the benchmark each carry their own identifier, and nothing enters training without an entry in the source registry.

Omnis Base

An adapted open-weight model for real product workloads.

Training a capable general model from scratch is a nine-figure problem. Adapting a strong, permissively-licensed open-weight model to our own tasks is not — and it ships today.

Omnis Base is our adaptation track. We take an open-weight base model with a commercially usable licence, then train low-rank adapters against benchmarks derived from our own products rather than generic leaderboards.

Five successive adapter generations have been trained and evaluated so far, each one a measured step rather than a guess. The adapters target every attention and feed-forward projection in the model, which is what lets a small number of trained parameters move behaviour meaningfully.

Self-hosting rather than renting an API matters for four reasons: we control the cost, the latency, the availability, and where customer data goes. The gateway interface stays identical when our own models take over.

omnis-base · adapter series 1.1 → 1.5

Adaptation setup

MethodLoRA (low-rank adaptation)
Rank16
Alpha32
Dropout0.05
Targetsall 7 projections
Adapter generations5
Base modelopen-weight, permissive licence

Deployed behind the Omnis Gateway, where routing, fallback and per-provider measurement are handled centrally.

The Omnis ladder

Each stage exists to make the next one cheaper to get right.

We do not skip stages. Every failure at the smallest size costs hours; the same failure at the largest costs six figures.

Complete

Omnis Tiny 0.1

Good for: nothing user-facing. It proves the stack — data pipeline, tokenizer, architecture, training loop, evaluation harness — works end to end.

Next

Omnis Tiny 1.0

Good for: language identification, text classification, and quality filtering for our own data pipeline. Useful internally, not externally.

Target

Omnis Small 1.0

The first genuinely shippable model. Yorùbá, Igbo and Hausa translation, autocomplete, extraction, classification and narrow assistants. This is the real target, and it is within reach of a funded round rather than a nine-figure one.

Later

Omnis Base 1.0 and beyond

Good for: a real assistant — instruction following, retrieval-augmented generation and tool use. Larger still only if the business demands it and revenue funds it.

Where a small model beats a large one

A one-billion-parameter model that is the best in the world at Yorùbá is a far better business than a thirty-billion-parameter model that is fortieth-best at English. Frontier labs are weak on African languages, local curricula and local business context — not because they cannot be strong, but because the data is not on the open web and the market is too small for them to prioritise. That weakness is structural, it is measurable, and it is defensible.

The Omnis Gateway

One API. Swappable backends.

No AfriStack product ever calls a model directly. Every product calls the gateway, and the gateway decides which model answers — so Omnis can take over one capability at a time, as soon as the numbers say it is ready.