---
title: "Llama 3, a fine-tuned LLM for a bank"
description: "Bank LLM: STEPS fine-tuned Llama 3 on Afreximbank's internal data, an open source model hosted and controlled by the bank."
canonical: https://steps.tn/en/bank-llm/
last-updated: 2026-11-16
---

# Llama 3, a fine-tuned LLM for a bank

Bank LLM: STEPS fine-tuned Llama 3 on Afreximbank's internal data, an open source model hosted and controlled by the bank.

URL: https://steps.tn/en/bank-llm/

Case study | Sovereign LLM, Afreximbank

Llama 3, an LLM fine-tuned on the bank's data

For Afreximbank, STEPS fine-tuned Llama 3 on the bank's internal data: corpus building, training, evaluation and deployment of an open source model the bank stays in control of.

× STEPS Case study | Sovereign LLM, Afreximbank 

## Llama 3, an LLM fine-tuned on the bank's data

 For Afreximbank, STEPS fine-tuned Llama 3 on the bank's internal data: corpus building, training, evaluation and deployment of an open source model the bank stays in control of.
 Open source model Internal data Secure deployment 
 Book my scoping session ↗
 
 $ prepare_corpus --source internal_docs
✓ corpus cleaned, deduplicated, anonymised
$ finetune --base llama-3 --method lora
epoch 3/3
$ evaluate --suite bank_qa --guardrails on
✓ model deployed on the bank's infrastructure
 01 - The context

## Generative AI, but not at any price

The bank wanted to use generative AI on its own documentation: reports, policies, internal notes. But off-the-shelf solutions raised confidentiality and relevance issues.
!Sensitive documentsA bank's internal data cannot be entrusted to an external service without guarantees.
!Specialised vocabularyGeneral-purpose models know little about trade finance and the bank's own language.
!A dependency to avoidBuilding on a proprietary API means depending on its prices, rules and availability.
 02 - The choice

## Why a model of its own rather than an API

A bank cannot send its internal documents just anywhere. A fine-tuned open source model stays under its control.
GENERAL-PURPOSE LLM VIA API

## Convenient, but

Data sent to a third party
Business vocabulary poorly handled
Dependency on a vendor
FINE-TUNED LLAMA 3

## The bank's choice

Model hosted and controlled by the bank
The bank's language and context learned
Guardrails defined in-house
 03 - The approach

## From corpus to model in production

01CorpusCollection, cleaning and anonymisation of internal documents.
02Fine-tuningTraining Llama 3 on this corpus, in the bank's vocabulary.
03EvaluationAnswer quality tests and guardrails before any go-live.
04Go-liveSecure deployment, controlled access and production monitoring.
 04 - The uses

## Querying the bank's documents

The model powers an information retrieval platform: teams upload their documents and ask questions in natural language, with built-in feedback.
 05 - The benefits

## What the model brings to the bank

An AI asset the bank owns, controls and can evolve.
Main benefitSovereignty over its AIThe bank has a language model tailored to its business, hosted and controlled by it: its data never leaves and it decides how the model evolves.
ConfidentialityProtected dataThe corpus and the model stay in a controlled environment.
RelevanceBusiness-aware answersThe model understands the bank's vocabulary and context.
CostsNo pay-per-use billingAn open source model avoids paying a vendor for every request.
IndependenceNo vendor lock-inThe model can be retrained, moved or replaced freely.
ProductivityFaster searchTeams find information in documents using natural language.
FoundationA base for other usesThe same model powers assistants, summaries and AI agents.
 06 - Our work

## Four phases, from idea to model in production

PHASE 01ScopingChoice of use cases, documents to include and confidentiality rules.
PHASE 02DataCollection, cleaning, anonymisation and structuring of the training corpus.
PHASE 03TrainingLlama 3 fine-tuning, iterations and evaluation on business questions.
PHASE 04ProductionSecure deployment, search platform and user feedback loop.
 07 - Architecture

## Under the hood

A complete MLOps chain, from data preparation to production monitoring.
Llama 3Fine-tuningLoRAPythonRAGMLOpsDataInternal corpus cleaned, deduplicated and anonymised
ModelOpen source Llama 3, fine-tuned on the bank's corpus
EvaluationBusiness question sets and safety guardrails
ServingHosted in an environment controlled by the bank
InterfaceInformation retrieval platform with user feedback
 FAQ

## Frequently asked questions

Why Llama 3?It is a high-performing open source model: the bank can host it, adapt it and evolve it without depending on a vendor.
Does the data leave the bank?No. The corpus, training and serving stay in an environment controlled by the bank.
Does training need to be redone regularly?The model can be retrained when the corpus evolves; the approach is documented and reproducible.
 Want generative AI that stays in-house? Let's talk about your sovereign LLM.
Book a scoping session ↗

---

Book a free scoping session: https://steps.tn/reserver-une-session-de-cadrage/

Site guide for agents: https://steps.tn/llms.txt
