atlas-institute

qwen35-08b-triage-grpo

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.

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
SFT adapter	atlas-institute/qwen35-08b-triage-sft
Method	GRPO (DeepSeekMath)
Prompt dataset	atlas-institute/code-trainer-v11-grpo-triage
Prompts	200 routing prompts

Validation Gate

Routing accuracy ≥ 0.90

Pipeline Chain

text

Qwen/Qwen3.5-0.8B  └─ SFT → atlas-institute/qwen35-08b-triage-sft      └─ GRPO → atlas-institute/qwen35-08b-triage-grpo  ← you are here          └─ 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-grpo")tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3.5-0.8B") messages = [{"role": "user", "content": "Analyze the /etc/passwd file for suspicious accounts"}]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-explore", "confidence": 0.92}

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

Citations

bibtex

@article{shao2024deepseekmath,    title        = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},    author       = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},    year         = 2024,    eprint       = {arXiv:2402.03300},}

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