Delentia

delentia-lora-scribe-v0.4

Deploy Dedicated

README

License: apache-2.0

Core Mechanics

Recursive Summarization: Condenses long historical chat context into a structured, minimal TOON representation.
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:

python

from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel base_model_name = "Delentia/delentia-slm-jitna-v0.4"adapter_name = "Delentia/delentia-lora-scribe-v0.4" # Load base model & tokenizermodel = AutoModelForCausalLM.from_pretrained(base_model_name)tokenizer = AutoTokenizer.from_pretrained(base_model_name) # Load adaptermodel = 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.

Table with columns: Component / Role, Deployment Type, Hugging Face Repository, Description, GGUF Support
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)

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: $\geq 74.0%$ )
- Average Context Compression Ratio: 30.96x (Target Gate: $\geq 3.5 x$ )

🔒 Empirical Audit Ledger

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

Empirical Performance Graph

Auditor Notebook: colab_4_pillars_v043.ipynb (GitHub Source) |
Run ID: a5541e6e
Target Safetensors Hash: SHA256:2f65b2d5ef2da4eac25e441e41481ff1ef9ce72621bbbbdf615f1a8b273959c2
Last Certified: 2026-07-13T06:26:20Z

Table with columns: Gate Category, Specific Metric, Target, Empirical Result, Status
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%

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Container

Run this model inference with full control and performance in your environment.

Learn more

Model Details

Model Provider

Delentia

Model Tree

Base

Delentia/delentia-slm-jitna-v0.4

Adapter

this model

Input Modalities

Text

Output Modalities