🌍 OjaLM-v0.1 — African Commerce Language Model
OjaLM-v0.1 is a specialized, domain-adapted commerce language model and AI foundation engineered for African markets.
Developing AI for African trade requires moving beyond generic foundation models. Informal and semi-formal open-air trade accounts for over 80% of retail commerce across Sub-Saharan Africa, moving hundreds of billions of dollars annually across hub markets such as Mile 12 (Lagos), Bodija (Ibadan), Dawanau (Kano), Onitsha Main Market (Anambra), and Gikomba (Nairobi).
Generic foundation models frequently hallucinate price data, fail to understand localized non-standard trade units (dericas, painter buckets, 50kg bags, metric tonnes), and lack awareness of regional market closures, transport strikes, or seasonal supply disruptions.
OjaLM addresses this challenge by focusing on a specific, high-impact goal:
Building AI systems that can understand, reason about, and enable autonomous agents to operate within African commerce.
Developed by
Ctrl+Prompt, OjaLM serves as the AI foundation layer powering
MamaPrice (
https://mamaprice.shop) — the real-time commerce intelligence application and agentic evaluation platform.
📌 System Architecture
OjaLM does not attempt to memorize rapidly fluctuating daily market prices inside static model weights. Instead, it separates language intelligence from live commerce data through OjaGraph v2 — a multi-modal Retrieval-Augmented Generation (RAG) graph.
1 OjaLM
2 AI Foundation Layer
3 │
4 ▼
5 OjaGraph
6 Commerce Knowledge Layer
7 │
8 ▼
9 MamaPrice
10 Commerce Intelligence App
11 │
12 ┌────────┴────────┐
13 ▼ ▼
14 Users / Apps AI Agents
Data & Execution Flow:
1User / Agent Query
2 │
3 ▼
4 OjaLM (Intent Detection & Query Parsing)
5 │
6 ▼
7 OjaGraph (Multi-Channel RAG Evidence Retrieval)
8 │
9 ├── Verified Price Indices & Spreads
10 ├── Active Market Disruptions & Events
11 ├── Availability & Shortage Reports
12 ├── Trend Memory & Historical Movement
13 └── Vendor Reliability Ratings
14 │
15 ▼
16 OjaLM (Grounded Reasoning & JSON Structuring)
17 │
18 ▼
19 Clean Conversational Answer / Machine-Readable API Payload
📊 Model Specifications
| Parameter | Specification |
|---|
| Model Name | OjaLM-v0.1 |
| Model Type | Causal Language Model |
| Base Model Family | Qwen3.5 (Qwen/Qwen3.5-4.8B) |
| Parameters | ~4.8 Billion parameters |
| Quantization Format | GGUF / Q4_K_M |
| Model File Size | ~3.07 GB |
| Embedding Dimension | 2,560 |
| Feed Forward Length | 9,216 |
| Vocabulary Size | 248,320 |
| Tensor Count | 427 |
| GGUF Version | 3 |
| Primary Cloud Runtime | Modal Cloud (Nvidia L4 GPU) / Hugging Face Serverless |
| Primary Local Runtime | llama.cpp / node-llama-cpp |
🚀 Key Capabilities
🛒 1. Commerce-Oriented Intelligence
- Commodity Price Interpretation: Accurate understanding of price quotes across agricultural staples (Rice, Tomatoes, Pepper, Garri, Palm Oil), construction materials (Dangote Cement, Rebar Steel), and energy (PMS Petrol).
- Localized Unit Conversions: Seamless translation between non-standard trade units (painter buckets, dericas, 50kg bags, crates) and standardized weights/metrics.
- Multi-Market Arbitrage Reasoning: Comparing price spreads between wholesale hubs (e.g., Mile 12 vs. Balogun Market in Lagos; Bodija vs. Dugbe in Ibadan).
🌍 2. Regional African Context
- Commercial Terminology: Native recognition of West & East African market slang, vendor negotiations, payment terms, and trading norms.
- Disruption Awareness: Factoring active market closures, maintenance schedules, seasonal rain/flood impacts, and transport strikes into commerce responses.
🛡️ 3. Strict Grounding & Anti-Hallucination
- Intent-Scoped Retrieval: Automatically distinguishes casual greetings (
"hello", "who are you?") from active commerce queries, bypassing evidence injection for general conversation to keep output direct and clean.
- Sanitized Completion Outputs: Strips internal chain-of-thought scratchpad text (
<think>...</think>) before returning JSON payloads to client applications.
🤖 4. Agentic Commerce Infrastructure (x402)
Designed from the ground up to support autonomous agentic workflows:
- Machine-Readable Tool Outputs: Formats structured
OjaData JSON blocks alongside natural language responses.
- Autonomous Procurement: Enables agents to query price feeds, evaluate vendor ratings, and execute machine-to-machine micropayments over Base / USDC using the
x402 protocol.
🏗️ Deployment & Inference Cascade
To ensure 99.99% operational availability and zero-hang cold-start protection, OjaLM runs within a fault-tolerant 4-Tier Inference Cascade:
1POST /chat Request
2 │
3 ├──► Attempt 1: Modal Cloud GPU (Nvidia L4, 5s timeout) ──► [ojalm-modal]
4 │
5 ├──► Attempt 2: Serverless Inference API ───────────────► [ojalm-hf]
6 │
7 ├──► Attempt 3: Local CPU GGUF (node-llama-cpp, 4s timeout) ► [ojalm-local]
8 │
9 └──► Tier 4 Fallback: OpenRouter Router + Grounded Static Snapshot ──► [openrouter / static]
🧪 Evaluation: OjaBench
OjaLM is benchmarked against OjaBench-v1, a domain-specific evaluation suite created by Ctrl+Prompt to test AI performance across African commercial contexts:
| Benchmark Category | Target Metric | OjaLM-v0.1 Focus |
|---|
| Product & Unit Reasoning | Unit Conversion Accuracy | 94.2% accuracy on regional trade unit conversions |
| Comparative Market Arbitrage | Wholesale Spread Calculation | Accurate ranking of cheapest vs. nearest market hubs |
| Retrieval Grounding | Hallucination Prevention | 0% price fabrication when OjaGraph evidence is supplied |
| Disruption Contextualization | Event-Aware Guidance | Recommends active alternative markets during closures |
| Structured Output Quality | Valid JSON Payload Rate | 99.1% valid OjaData JSON output compliance |
💻 Usage Example
Running OjaLM via Node.js (node-llama-cpp):
1import { getLlama, LlamaChatSession } from "node-llama-cpp";
2import path from "path";
3
4const llama = await getLlama();
5const model = await llama.loadModel({
6 modelPath: path.join(__dirname, "models", "OjaLM-v0.1.gguf")
7});
8
9const context = await model.createContext({ contextSize: 512 });
10const session = new LlamaChatSession({ contextSequence: context.getSequence() });
11
12const prompt = `GROUNDED OJAGRAPH COMMERCE EVIDENCE:
13• 50kg Bag Rice at Mile 12 Market, Lagos: ₦82,000 per bag — Confidence: 95%
14
15USER QUESTION: What is the price of a bag of rice in Mile 12?`;
16
17const response = await session.prompt(prompt, { maxTokens: 200 });
18console.log("OjaLM Response:", response);
⚠️ Limitations & Responsible AI Guidelines
- Parametric Memory vs. Live Data: OjaLM should never be used as a standalone static source of truth for dynamic daily prices. Always pair OjaLM with OjaGraph or an active price feed.
- Financial & Contractual Decisions: Price estimates and vendor ratings should be verified with field scouts or merchants before committing to high-stakes procurement contracts.
- Geographic Coverage: Current v0.1 evaluation focuses heavily on Nigeria, Kenya, Ghana, and South Africa. Coverage for additional regional markets is actively expanding.
📄 License
Distributed under the MIT License.
📚 Citation & Acknowledgments
If you use OjaLM, OjaGraph, or OjaBench in your research or application, please cite:
1@misc{ojalm2026,
2 title = {OjaLM-v0.1: An African Commerce Language Model & Intelligence Foundation},
3 author = {Ctrl+Prompt},
4 year = {2026},
5 publisher = {Hugging Face},
6 howpublished = {\url{https://huggingface.co/ctrlprompt/OjaLM-v0.1}},
7 note = {Fine-tuned Qwen3.5 4.8B model for African commerce, markets, and agentic workflows}
8}
Acknowledgments
OjaLM builds upon the open-weights ecosystem, acknowledging the contributions of:
- Qwen Team (
Qwen/Qwen3.5-4.8B)
- Modal Labs (Cloud GPU Infrastructure)
- Base / Coinbase Developer Platform (
x402 Agent Payment Standards)
- African AI initiatives including N-ATLaS and AfriqueQwen.
Developed by Ctrl+Prompt · Flagship Application: MamaPrice
