Delentia/delentia-lora-scribe-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 Scribe v0.4 (slm-jitna-scribe-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 Scribe is a specialized context compression LoRA adapter in the Delentia OS 1+4 Pillar Architecture. It resolves context window saturation by performing recursive text summarization.

Core Mechanics

1. Recursive Summarization: Condenses long historical chat context into a structured, minimal TOON representation.
2. Noise Reduction: Filters out colloquial conversational elements, keeping only actionable parameters.

⚡ Quick Start: Load Adapter via PEFT

To execute this specialized generative context-compression 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-scribe-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.

Component / Role	Deployment Type	Hugging Face Repository	Description	GGUF Support
SLM Base Kernel	Base Foundation	Delentia/delentia-slm-jitna-v0.4	Core cognitive LLM (8B Parameters)	✅
The Router	PEFT LoRA Adapter	Delentia/delentia-lora-router-v0.4	Intention parser & node routing	❌ (PEFT only)
The Executor	PEFT LoRA Adapter	Delentia/delentia-lora-executor-v0.4	JSON tool payload generation	✅ (Merged GGUF below)
The Guardian	PEFT LoRA Adapter	Delentia/delentia-lora-guardian-v0.4	Zero-trust constitutional safety	✅ (Merged GGUF below)
The Scribe	PEFT LoRA Adapter	Delentia/delentia-lora-scribe-v0.4	Context compression/summarization	✅ (Merged GGUF below)
Pre-Merged Executor	Pre-Merged GGUF	Delentia/delentia-slm-jitna-executor-v0.4	Complete tool executor (plug-and-play)	✅
Pre-Merged Guardian	Pre-Merged GGUF	Delentia/delentia-slm-jitna-guardian-v0.4	Full safety guardrail model	✅
Pre-Merged Scribe	Pre-Merged GGUF	Delentia/delentia-slm-jitna-scribe-v0.4	Out-of-the-box context compressor	✅

• Ecosystem Datasets:
  • 📖 RAG Corpus Dataset — source material for long-document parsing.
  • 📊 Intent Training Dataset

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):
  • Long-term Token Savings: 92.57% (Target Gate: $\ge 74.0%$)
  • Average Context Compression Ratio: 30.96x (Target Gate: $\ge 3.5\text{x}$)

---

🔒 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: SHA256:2f65b2d5ef2da4eac25e441e41481ff1ef9ce72621bbbbdf615f1a8b273959c2
• Last Certified: 2026-07-13T06:26:20Z

Gate Category	Specific Metric	Target	Empirical Result	Status
Silicon Attestation	PCIe VRAM Swap Latency	< 12.0 ms	11.1000 ms	Certified (Cloud)
Context Window	Max Token Savings %	>= 15.00%	485.98%	Certified
Information Gate	NIAH Memory Recall Accuracy	= 100%	100.00%	Certified