atlas-institute

qwen35-08b-triage-sft

README

License: apache-2.0

Swarm Role

The triage agent is the entry point for the NEXUS swarm. It classifies incoming requests and routes them to the correct swarm node. It runs on an RK3588 NPU (6 TOPS) on the Orange Pi 5 Plus.

Input: Any user request
Output: JSON classification — {"category": "...", "route": "...", "confidence": 0.0-1.0}

Categories: recon, exploit, code-review, report, admin, unknown

Routing Rules:

Table with columns: Pattern, Route
Pattern	Route
Complex multi-step tasks	`nexus-orchestrator`
Simple single-tool tasks (scan, edit, run)	`nexus-worker`
Search, read, classify tasks	`nexus-explore`
Unsure	`nexus-orchestrator` (fallback)

Training Details

Table with columns: Parameter, Value
Parameter	Value
Base model	Qwen/Qwen3.5-0.8B
Method	SFT with LoRA (PEFT)
Dataset	atlas-institute/code-trainer-v11-triage
Training rows	5,000
Epochs	3
Max sequence length	512
LoRA rank / alpha	16 / 32

Validation Gate

Routing accuracy ≥ 0.85

Pipeline Chain

text

Qwen/Qwen3.5-0.8B  └─ SFT → atlas-institute/qwen35-08b-triage-sft  ← you are here      └─ GRPO → atlas-institute/qwen35-08b-triage-grpo          └─ RKLLM → w8a8 for RK3588 NPU

Usage

python

from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel base_model = AutoModelForCausalLM.from_pretrained(    "Qwen/Qwen3.5-0.8B", torch_dtype="bfloat16", device_map="auto")model = PeftModel.from_pretrained(base_model, "atlas-institute/qwen35-08b-triage-sft")tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3.5-0.8B") messages = [{"role": "user", "content": "Run nmap against 10.10.10.1 and report open ports"}]inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to(model.device)outputs = model.generate(inputs, max_new_tokens=64)print(tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True))# Expected: {"category": "recon", "route": "nexus-worker", "confidence": 0.95}

Swarm Topology

Table with columns: Node, GPU, Role, Model
Node	GPU	Role	Model
nexus-k1	RTX 5060 Ti 16 GB	Orchestrator	Qwen3-14B Q4_K_M
nexus-control	RTX 3070 8 GB	Worker	Qwen3-8B Q4_K_M
nexus-3060	RTX 3060 6 GB	Explore	Gemma-3-4B-it Q8_0
nexus-opi5p	RK3588 NPU 6 TOPS	Triage

Developed By

Atlas Institute — Code-Trainer / RTPI pipeline

Available on FriendliAI

Dedicated Endpoints

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

Learn more

Model Details

Model Provider

atlas-institute

Model Tree

Base

Qwen/Qwen3.5-0.8B

Adapter

this model

Input Modalities

TextImageVideo

Output Modalities

Text

Supported Functionality