Plek-1 Decision Model

Plek-1 is a System One Decision Model designed for high-speed, non-autoregressive decision classification inspired by the Jev methodology.

Unlike standard autoregressive generative models that produce text token-by-token, Plek-1 runs non-autoregressively: it evaluates candidate choices in parallel via single-pass sequence log-likelihood scoring and outputs calibrated probability distributions and structured decision JSONs without risk of text hallucinations.

💡 Inspiration & Architecture: Jev-Style System One Decisions

Standard LLMs generate text token-by-token, which can be slow, expensive, and prone to text hallucinations.

Plek-1 implements the Jev System-One methodology:

1. Non-Autoregressive Scoring: Evaluates candidate choices simultaneously in a single forward pass.
2. Zero-Hallucination: Restricts outputs to exact candidate option log-likelihoods and calibrated probability distributions.
3. High Throughput: Delivers low-latency structured JSON decisions for routing, intent detection, and safety filters.

Usage

import torch
from transformers import AutoModel, AutoTokenizer

# 1. Load Plek-1 from Hugging Face Hub (with custom code support)
model_id = "Drenel/plek-1"
model = AutoModel.from_pretrained(model_id, trust_remote_code=True)

# 2. Define Context and Candidate Choices
context = "The system crashed with error code 500 when processing the checkout page."
choices = ["Billing Issue", "Technical Bug", "Feature Request", "Spam"]

# 3. Predict Probability Distribution
result = model.predict(context=context, choices=choices)

print("Prediction:", result["prediction"])
print("Confidence:", result["confidence"])
print("Full Probabilities:", result["probabilities"])

Multi-Field Structured Decision Schema

schema = {
    "intent": ["Billing Query", "Technical Support", "General Inquiry"],
    "urgency": ["Low", "Medium", "High", "Critical"],
    "sentiment": ["Positive", "Neutral", "Negative"]
}

customer_message = "I was charged twice on my credit card and need a refund immediately!"
structured_result = model.predict_structured(context=customer_message, schema=schema)

Ultra-Long Context Evaluation (200,000+ Tokens)

huge_document = open("large_contract.txt").read()
result = model.predict_long(
    long_context=huge_document,
    choices=["Compliant Contract", "High-Risk Liability", "Non-Binding Terms"]
)