---
license: apache-2.0
base_model: unsloth/Meta-Llama-3.1-8B-bnb-4bit
tags:
- text-classification
- peft
- lora
- delentia-os
- JITNA
- multi-adapter
- sequence-classification
---

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

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.

## 🔗 JITNA Ecosystem Links
To ensure proper routing operations, developers must configure JITNA to load the associated components:
* **Core Foundation Base:** [Delentia/delentia-slm-jitna-v0.4](https://huggingface.co/Delentia/delentia-slm-jitna-v0.4)
* **Sibling Adapters:**
  * ⚡ [The Executor v0.4](https://huggingface.co/Delentia/delentia-slm-jitna-executor-v0.4)
  * 🛡️ [The Guardian v0.4](https://huggingface.co/Delentia/delentia-slm-jitna-guardian-v0.4)
  * 📜 [The Scribe v0.4](https://huggingface.co/Delentia/delentia-slm-jitna-scribe-v0.4)
* **Training Dataset:** [Delentia/delentia-rct-intent-dataset](https://huggingface.co/datasets/Delentia/delentia-rct-intent-dataset)

## 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.