ModelPublicadoExterno

Delentia LoRA Router v0.4

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

Fuentehuggingface.co/Delentia/delentia-lora-router-v0.4/tree/fb21b5b48f36e592cf7793d49305d49ddfbfb150

TipoLoRAModelo baseDelentia/delentia-slm-jitna-v0.4VersiónFP32Unratedcalidad

Fuente del modelo

Tipo: LoRA
Tamaño del archivo: 26,1 MB
Modelo base: Delentia/delentia-slm-jitna-v0.4
Versión: vFP32
Actualizado: 3 nov 2026
Descargas: 15
Fuente: Hugging Face

Descripción de la fuente

⚙️ 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.

Open In Colab

Delentia SLM — The Router v0.4 (slm-jitna-router-v0.4)

GitHub Stars GitHub Forks

⚙️ 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 Router is a specialized Sequence Classification LoRA adapter within the Delentia OS 1+4 Pillar Architecture. Its primary role is to intercept incoming user intents and classify them into one of the specialized execution pathways at ultra-low latency.

⚡ Quick Start: Load Adapter via PEFT

To execute this specialized classification adapter, load it on top of the base model:

from transformers import AutoModelForSequenceClassification, AutoTokenizer
from peft import PeftModel

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

# Load base model & tokenizer
model = AutoModelForSequenceClassification.from_pretrained(base_model_name, num_labels=4)
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	✅

Technical Specifications

Base Model: unsloth/Meta-Llama-3.1-8B-bnb-4bit
Fine-Tuning Method: Sequence Classification QLoRA (SEQ_CLS adapter config)
Target Modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
Output Labels:
- 0: Router Base (Conversational / Standard Prompt)
- 1: Executor (Tool / JSON Execution)
- 2: Guardian (Safety Shield evaluation)
- 3: Scribe (Context compression/summarization)

Certified GPU Runs (v0.4 Performance)

Routing Classification Accuracy: 100.00% (Target Gate: $\ge 96.0%$)
VRAM Swap Latency: 11.2 milliseconds (Target Gate: $\le 12.0\text{ms}$)
Inference Speed: 20-50 milliseconds on consumer-grade local hardware.

🔒 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) | Open In Colab
Run ID: a5541e6e
Target Safetensors Hash: SHA256:0a1a9dec583c2259904b7504fd3483ea47563bce5257f5740d197ada173cb83a
Last Certified: 2026-07-13T06:26:20Z

Gate Category	Specific Metric	Target	Empirical Result	Status
Silicon Attestation	PCIe VRAM Swap Latency	< 12.0 ms	11.2000 ms	Certified (Cloud)
Cognitive Routing	Intent Classification Accuracy	>= 96.00%	100.00%	Certified
Economic Gate	API Cost Reduction Ratio	>= 90.00%	99.40%	Certified

Fuentes

1 fuente

Hugging FacePrincipalVersión fb21b5b48f36e592cf7793d49305d49ddfbfb150

huggingface.co/Delentia/delentia-lora-router-v0.4/tree/fb21b5b48f36e592cf7793d49305d49ddfbfb150

Verificado 3 nov

Download files

Repository files

File inventory only; completeness is unverified.

Artefactos del modelo

1 artefacto

adapter_model.safetensors

safetensors · FP32 (tensor header) · 26,1 MB · SHA-256 ca125608184c…59b1 · Hugging Face

Download file

Extractos de fuentes

3 extractos

Readme23 agohuggingface.co/Delentia/delentia-lora-router-v0.4

--- license: apache-2.0 base_model: Delentia/delentia-slm-jitna-v0.4 tags: - text-classification - peft - lora - delentia-os - JITNA - multi-adapter - sequence-classification --- [⚙️ GitHub SDK](https://github.com/delentia-labs/Delentia-OS) | [GitHub Source](https://github.com/delentia-labs/Delentia-AI-SLM/blob/main/notebooks/v0.4.3/colab_4_pillars_v043.ipynb) | [Live Auditor (Google Colab)](https://colab.research.google.com/github/delentia-labs/Delentia-AI-SLM/blob/main/notebooks/v0.4.3/colab_4_pillars_v043.ipynb) | [SHA256 - Verified Purity](README#empirical-audit-ledger) | [DOI: 10.5281/zenodo.20920052](https://doi.org/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. > > [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/delentia-labs/Delentia-AI-SLM/blob/main/notebooks/v0.4.3/colab_4_pillars_v043.ipynb) --- # Delentia SLM — The Router v0.4 (slm-jitna-router-v0.4) [![GitHub Stars](https://img.shields.io/github/stars/delentia-labs/Delentia-OS?style=social)](https://github.com/delentia-labs/Delentia-OS) [![GitHub Forks](https://img.shields.io/github/forks/delentia-labs/Delentia-OS?style=social)](https://github.com/delentia-labs/Delentia-OS) > ⚙️ **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)](https://github.com/delentia-labs/Delentia-OS)** --- The Router is a specialized Sequence Classification LoRA adapter within the **Delentia OS 1+4 Pillar Architecture**. Its primary role is to intercept incoming user intents and classify them into one of the specialized execution pathways at ultra-low latency. ## ⚡ Quick Start: Load Adapter via PEFT To execute this specialized classification adapter, load it on top of the base model: ```python from transformers import AutoModelForSequenceClassification, AutoTokenizer from peft import PeftModel base_model_name = "Delentia/delentia-slm-jitna-v0.4" adapter_name = "Delentia/delentia-lora-router-v0.4"...

Note3 novhuggingface.co/Delentia/delentia-lora-router-v0.4

Source context: 15 downloads · 0 likes · Pipeline text-classification · Library peft · Repo Delentia/delentia-lora-router-v0.4

Note23 agohuggingface.co/Delentia/delentia-lora-router-v0.4

Source context: 18 downloads · 0 likes · Pipeline text-classification · Library peft · Repo Delentia/delentia-lora-router-v0.4