delentia-lora-executor-v0.4

⚙️ GitHub SDK | GitHub Source | Live Auditor (Google Colab) | SHA256 - Verified Purity | DOI: 10.5281/zenodo.20920052

🛡️ Attest the Performance Live on Free T4 GPU

We challenge any technical reviewer, auditor, or developer to verify our systems benchmarks. Click the badge below to run the clean-room auditor on a free Google Colab T4 GPU instance. No private credentials or Drive mounts are required.

---

Delentia SLM — The Executor v0.4 (slm-jitna-executor-v0.4)

⚙️ Looking for the SDK & Source Code?
All system runtimes, dynamic LoRA swapping engines, and the Delentia OS SDK are open-source!
👉 Star & Fork the repository on GitHub (delentia-labs/Delentia-OS)

---

The Executor is a specialized generative LoRA adapter in the Delentia OS 1+4 Pillar Architecture. It is trained specifically to translate raw user intents into machine-executable JSON/TOON payloads.

Key Principles

1. Zero Conversational Bias: Output is strictly restricted to valid, raw JSON/TOON format. It never generates conversational fillers or explanations.
2. Deterministic Tool Invocation: Correctly maps tools, parameters, and system state boundaries with zero hallucinations.

⚡ Quick Start: Load Adapter via PEFT

To execute this specialized generative tool-calling adapter, load it on top of the base model:

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_model_name = "Delentia/delentia-slm-jitna-v0.4"
adapter_name = "Delentia/delentia-lora-executor-v0.4"

# Load base model & tokenizer
model = AutoModelForCausalLM.from_pretrained(base_model_name)
tokenizer = AutoTokenizer.from_pretrained(base_model_name)

# Load adapter
model = PeftModel.from_pretrained(model, adapter_name)

🌐 Delentia OS Ecosystem Model Roster (v0.4.x)

Delentia OS is organized into two primary deployment styles: Dynamic PEFT Adapters (1+4 Pillars) for sub-ms switching in unified VRAM, and Pre-Merged GGUF Models for direct plug-and-play local execution in Ollama / llama.cpp.

Technical Specifications

• Base Model: unsloth/Meta-Llama-3.1-8B-bnb-4bit
• Format: PEFT LoRA adapter (Rank = 32, Alpha = 64) / GGUF Q4_K_M
• Certified GPU Runs (v0.4 Performance):
  • Tool Calling Accuracy: 98.00% (Target Gate: $\ge 95.0%$)
  • JSON/TOON Format Validity: 98.00% (Target Gate: $\ge 99.0%$)

---

🔒 Empirical Audit Ledger

The domain-specific empirical results below were generated and certified via system digital forensics:

• Auditor Notebook: colab_4_pillars_v043.ipynb (GitHub Source) |
• Run ID: a5541e6e
• Target Safetensors Hash: SHA256:45adecde0dc7a23e23c6681a46c9fa831be779001baaeefc60e5c388384954f9
• Last Certified: 2026-07-13T06:26:20Z