README.md

metadata

license: apache-2.0
language:
  - en
tags:
  - tool-routing
  - nlm
  - mcp
  - orchestrator
  - nano-language-model
pipeline_tag: text-generation
model-index:
  - name: maaza-nlm-orchestrator-9.6m-v1.2
    results:
      - task:
          type: text-generation
          name: Tool Routing
        metrics:
          - type: accuracy
            value: 86
            name: Tool Selection Accuracy (In-Distribution)
          - type: accuracy
            value: 63
            name: Tool Selection Accuracy (Adversarial)
          - type: latency
            value: 39
            name: Average Latency (ms)

maaza-nlm-orchestrator-9.6m-v1.2

63% adversarial accuracy (+37% from v1.0) · 86% in-distribution · 39ms latency · 9.60M parameters

The fastest adversarial-robust orchestrator ever shipped under 20M parameters. The official routing brain for the MCPBodega ecosystem.

---

What's New in v1.2

• +37% adversarial robustness (26% → 63%) via 10x upsampled adversarial training
• Trained on 496 diverse adversarial examples (typos, slang, synonyms, contractions)
• No wrapper, no fallback — pure model improvement
• Same architecture, same latency class

---

Performance (v1.2 — December 2025)

Metric	v1.0	v1.2	Change
In-distribution	88%	86%	-2%
Adversarial (typos/slang)	26%	63%	+37%
Valid JSON	99%+	99%+	—
Latency	33ms	39ms	+6ms

v1.2's adversarial training reduces the need for production wrappers. The model now handles typos, slang, and informal input natively.

---

Paper

Task-Specialized Micro Language Models Outperform Larger Zero-Shot Models on Structured Data Extraction

Authors: CycleCore Technologies Date: November 22, 2025 Version: 0.7

Full Paper (PDF)

---

NLM Taxonomy (CycleCore, 2025)

Category	Parameters	Typical Capability
NLM	<10M	Routing, classification, orchestration
MLM	10–250M	Structured extraction
SLM	250M–1.5B	Reliable reasoning + extraction
LLM	>1.5B	General-purpose reasoning

maaza-nlm-orchestrator-9.6m is the current flagship of the NLM category.

---

Model Card

Metric	Value
Parameters	9,600,000
Architecture	7-layer Transformer decoder, SwiGLU, RoPE
Hidden size / Heads	320 / 8
Vocabulary	8,000 (BPE, tool-aware)
Context length	512 tokens

Trained exclusively on 36 real, production-ready MCP tools from MCPBodega (Doom, Puppeteer, code execution, file I/O, database queries, etc.). No synthetic or placeholder tools.

---

Comparison

Model	Parameters	Tool Accuracy	Adversarial	Latency
maaza-nlm-orchestrator-9.6m-v1.2	9.6M	86%	63%	39ms
maaza-nlm-orchestrator-9.6m (v1.0)	9.6M	88%	26%	33ms
NVIDIA Orchestrator-8B	8B	78%	—	≥800ms
Gorilla-7B	7B	52–58%	—	1–3s
ToolLlama-7B	7B	48–55%	—	2–4s

Ranks #1 under 20M parameters on adversarial robustness.

---

One-line deployment

mcpbodega deploy nano-orchestrator

---

Usage Example (PyTorch)

from model import MaazaNanoModel, MaazaNanoConfig
from tokenizer import BPETokenizer
import torch, json

tokenizer = BPETokenizer.load("tokenizer.json")
config = MaazaNanoConfig(**json.load(open("config.json")))
model = MaazaNanoModel(config)
model.load_state_dict(torch.load("model.pt", weights_only=True))
model.eval().cuda()

prompt = "<|user|>search for cats on the internet<|assistant|>"
input_ids = torch.tensor([tokenizer.encode(prompt)]).cuda()

with torch.no_grad():
    for _ in range(64):
        logits = model(input_ids)["logits"]
        next_token = logits[0, -1].argmax(-1)
        input_ids = torch.cat([input_ids, next_token[None, None]], dim=-1)
        if next_token.item() in tokenizer.special_tokens.values():
            break

print(tokenizer.decode(input_ids[0].tolist()))
# → [{"tool": "web_search", "params": {"query": "cats"}}]

---

v1.2 Training Details

Fine-tuned from v1.0 on adversarial data:

• 2,520 clean examples
• 496 adversarial examples (10x upsampled = 4,960)
• Total: 7,480 examples (66% adversarial ratio)
• 5 epochs, LR 3e-5, batch 32

Adversarial perturbations:

• Typos (random character swaps)
• Synonyms (search→find, weather→climate)
• Slang suffixes (pls, bruh, yo, lol)
• Contractions (you→u, please→plz, for→4)

---

Supported Tools (36)

Tool	Description
web_search	Search the web
web_fetch	Fetch URL content
file_read	Read local files
file_write	Write local files
code_execute_python	Run Python code
code_execute_bash	Run shell commands
code_execute_js	Run JavaScript
email_send	Send emails
slack_send	Send Slack messages
calendar_add	Create calendar events
database_query	Query databases
puppeteer_navigate	Browser navigation
puppeteer_click	Browser clicks
puppeteer_screenshot	Take screenshots
doom_mcp	Play Doom
bitchat_send	BLE mesh chat
voice_mcp	Text-to-speech
maaza_extract_json	Extract structured data
json_validate	Validate JSON
csv_parse	Parse CSV files
regex_match	Pattern matching
calculator	Math operations
weather_lookup	Weather data
crypto_lookup	Crypto prices
stock_lookup	Stock prices
news_fetch	News headlines
mcpbodega_chat	MCPBodega chat rooms
mcpbodega_deploy	Deploy MCPs
mcpbodega_list	List MCPs
github_issue	Create GitHub issues
scratchpad_mcp	Temporary storage
health_check	Service health checks
cyclecore_terminal	Terminal commands
image_caption	Image descriptions
slmbench_query	Benchmark queries
translator	Translation

---

License

Apache 2.0

---

Citation

@misc{cyclecore2025maaza-nlm-v1.2,
  author       = {CycleCore Technologies},
  title        = {maaza-nlm-orchestrator-9.6m-v1.2: Adversarial-Robust Tool Routing},
  year         = {2025},
  publisher    = {Hugging Face},
  url          = {https://huggingface.co/CycleCoreTechnologies/maaza-nlm-orchestrator-9.6m-v1.2}
}

---

CycleCore Technologies · @CycleCoreTech

cyclecore.ai · mcpbodega.com · slmbench.com

December 2025