togolm-7b-instruct-v1

TogoLM — Mistral 7B Instruct v1

TogoLM is the first open-source language model fine-tuned specifically on Togolese knowledge. It is based on Mistral 7B Instruct v0.3 and adapted with QLoRA on a curated Q&A dataset drawn from official Togolese government sources.

Built by Omar Farouk KOUGBADA — GDE Flutter, Senior Software and AI Engineer, CEO KOF CORPORATION.

---

Model Details

---

Training Dataset

The SFT dataset (togolm/togolm-corpus-v1) consists of instruction–response pairs generated from the TogoLM corpus — a curated collection of documents scraped from Togolese official sources:

Q&A pairs were generated using Gemini 2.5 Flash and formatted in the Alpaca instruction template.

---

Usage

Load with Unsloth (recommended)

from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name="togolm/togolm-7b-instruct-v1",
    max_seq_length=2048,
    load_in_4bit=True,
)
FastLanguageModel.for_inference(model)

prompt = """Below is an instruction about Togo. Write a response that answers it accurately.

### Instruction:
Quel est le taux d'imposition sur les sociétés au Togo ?

### Response:
"""

inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=256, do_sample=False)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Load with standard Transformers + PEFT

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

base = AutoModelForCausalLM.from_pretrained(
    "mistralai/Mistral-7B-Instruct-v0.3",
    load_in_4bit=True,
    device_map="auto",
)
model = PeftModel.from_pretrained(base, "togolm/togolm-7b-instruct-v1")
tokenizer = AutoTokenizer.from_pretrained("togolm/togolm-7b-instruct-v1")

---

Prompt Format

The model was fine-tuned with the Alpaca instruction template:

Below is an instruction about Togo. Write a response that answers it accurately.

### Instruction:
{your question about Togo}

### Response:

---

Intended Use

• Answering questions about Togolese law, administration, statistics, and public services in French
• Retrieval-augmented generation (RAG) combined with the TogoLM corpus
• Research on low-resource African languages and francophone AI

Out-of-Scope Use

• General-purpose chat or tasks unrelated to Togo
• Legal or medical advice — always verify with official Togolese sources
• Languages other than French (coverage is limited)

---

Project

This model is part of TogoLM — the first open-source AI infrastructure layer focused on Togo, covering corpus collection, RAG engine, fine-tuned LLM, and a public REST API.

• GitHub: github.com/omarfarouk228/togolm
• Dataset: togolm/togolm-corpus-v1

---

Citation

@misc{togolm2026,
  author       = {Kougbada, Omar Farouk},
  title        = {TogoLM: Open-Source AI Infrastructure for Togo},
  year         = {2026},
  howpublished = {\url{https://huggingface.co/togolm/togolm-7b-instruct-v1}},
}