You can deploy this model and start earning money today!

mjpsm/
Shujaa-xgb-model

Name: Shujaa-xgb-model
Availability: InStock

Views

No views yet

Shujaa XGBoost Model

The Shujaa XGBoost model is part of the Soulprint archetype framework.
It predicts a Shujaa score (0.00–1.00) for input text, representing levels of persistence, reliability, and consistent follow-through.

This model was trained on a balanced dataset of 1,026 rows, evenly distributed across Low, Mid, and High Shujaa ranges.
The dataset was carefully curated to avoid keyword bias and to promote generalization.

📊 Training Results

MSE: 0.0125
R²: 0.819

📦 Usage

Install dependencies:

python

pip install xgboost sentence-transformers huggingface_hub
import xgboost as xgb
from sentence_transformers import SentenceTransformer
from huggingface_hub import hf_hub_download

# -----------------------------
# 1. Download model from Hugging Face Hub
# -----------------------------
REPO_ID = "mjpsm/Shujaa-xgb-model"
FILENAME = "Shujaa_xgb_model.json"

model_path = hf_hub_download(repo_id=REPO_ID, filename=FILENAME)

# -----------------------------
# 2. Load model + embedder
# -----------------------------
model = xgb.XGBRegressor()
model.load_model(model_path)

embedder = SentenceTransformer("all-mpnet-base-v2")

# -----------------------------
# 3. Example prediction
# -----------------------------
text = "I carried my responsibility with persistence until it was complete."
embedding = embedder.encode([text])
score = model.predict(embedding)[0]

print("Predicted Shujaa Score:", round(float(score), 3))

🧩 Part of the Soulprint Framework

The Shujaa archetype represents courage, discipline, and persistence within the Soulprint framework. This model is one of several archetype regressors (e.g., Griot, Ubuntu, Kinara) trained on balanced datasets to predict culturally grounded narrative signals.