metafloor-ai/manifest-orchestrator-2b
Manifest 2B
The balanced workhorse of the Manifest suite — expert supply-chain answers at the best quality-to-cost ratio MetaFloor makes.
Manifest is MetaFloor's suite of supply-chain expert models — purpose-built specialists in procurement, demand planning, warehouse operations, supplier relationship management, risk & resilience, transportation, inventory, and order fulfilment.
- Family: Manifest · This model: Manifest 2B (2-billion-parameter base)
- Tier: balanced — the sensible default for most deployments
### Preferred 88.4% of the time over the base model On 116 held-out expert questions, an independent LLM judge panel picked Manifest 2B's answer over the untuned base model's answer 88.4% of the time (95% CI 82.8–93.5%) — top-tier quality at a fraction of the compute.
Best for
The everyday middle ground: strong reasoning, still light enough to run cheaply at scale.
- Day-to-day supply-chain Q&A and analysis
- Drafting recommendations, briefs, and playbooks
- In-product copilots and assistants that need real domain depth
- The default choice when you're not sure which size you need
(Need maximum depth? Manifest 4B. Need lowest cost / highest volume? Manifest 0.8B. Both below.)
See the difference
Same question. Base model vs Manifest 2B.
Ask (COO of a $5.8B enterprise, mostly manual): "Explain the core concept of MEIO and why it's relevant given our manual, single-echelon approach." Base model → "### Core Concept of Multi-Echelon Inventory Optimization (MEIO). MEIO is a strategic framework designed to optimize inventory levels across multiple distribution centers…" — a generic textbook definition. Manifest 2B → "MEIO is the discipline of deciding how much safety stock to hold at EACH level of a supply chain together, instead of treating each stocking point as an isolated problem…" — a decision-ready, practitioner's answer.
The Manifest family
Two kinds of models:
🧭 Orchestrators — general-purpose, handle any supply-chain area
🎯 Domain-experts — specialized for a single area
Orchestrators are scored on the general supply-chain benchmark; domain-experts on their focused domain benchmark.
Not just a model — a full stack
Manifest is backed by everything needed to build it and trust it:
- A purpose-built dataset — thousands of supply-chain instruction–response pairs spanning 8 sub-domains and every company scale, generated by a seed-driven operator-as-teacher pipeline.
- A reproducible training pipeline — documented LoRA fine-tuning.
- An independent benchmark — 116 held-out expert questions, scored blind by a panel of LLM judges.
We built the model, the data, and the evaluation.
How to use
Manifest 2B is a LoRA adapter (~61 MB), applied on top of its base model at load time.
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base = "Qwen/Qwen3.5-2B" # base model — see "Built on" below
tok = AutoTokenizer.from_pretrained(base)
model = AutoModelForCausalLM.from_pretrained(base, device_map="auto")
model = PeftModel.from_pretrained(model, "metafloor-ai/manifest-orchestrator-2b")
SYSTEM = "You are a senior supply chain expert. Answer correctly and concisely."
user = (
"I'm an inventory planner at a ~$8M small business: ~11k active SKUs, 4 suppliers, "
"2 network nodes, ~164-day avg lead time. How should I set safety stock as I move off spreadsheets?"
)
msgs = [{"role": "system", "content": SYSTEM}, {"role": "user", "content": user}]
inputs = tok.apply_chat_template(msgs, add_generation_prompt=True, return_dict=True, return_tensors="pt")
out = model.generate(**inputs, max_new_tokens=512, temperature=0.7)
print(tok.decode(out[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))Prompt tip: Manifest is trained to condition on the scenario — include the asker's role and operating scale (revenue, SKUs, suppliers, nodes, lead time) in the message for the sharpest, most tailored answers.
How it was measured
116 held-out expert questions across 8 supply-chain areas. Each question is answered by Manifest and by the base model (given the same answer format); an independent two-model LLM judge panel then picks the better answer. Manifest 2B was preferred 88.4% of the time (95% CI 82.8–93.5%; 100 wins / 11 losses / 5 ties over 116). Benchmark: [supply-chain-eval](https://huggingface.co/datasets/metafloor-ai/supply-chain-eval).
Training details
Training data: supply-chain instruction–response pairs from the seed-driven operator-as-teacher pipeline — a deterministic engine emits a unique seed per example (area, sub-area, persona, question type, realistic numeric scenario) and a strong teacher model writes the matching answer. The training data is drawn from MetaFloor's proprietary ~12.5k-example supply-chain dataset, which is not open-sourced — only the held-out evaluation benchmark (supply-chain-eval) is public.
Intended use & limitations
- Intended use: everyday decision-support and drafting for supply-chain professionals.
- Out of scope: not legally binding, contractual, or safety-critical guidance; no access to your live systems or real-time data. Verify outputs before acting on them.
- Limitations: English-only; trained on synthetic (model-authored) data; standard LLM risks (hallucination, outdated facts) apply.
License
Manifest models and the supply-chain-eval benchmark are released under CC-BY-NC-4.0 — free for research and non-commercial use, with attribution. Commercial use requires a license from MetaFloor — get in touch at metafloor.ai.
Built on
Manifest 2B is a LoRA adapter over Qwen/Qwen3.5-2B (used under its own license); the base model is required to load the adapter.
Citation
@misc{metafloor_manifest_2b,
title = {Manifest 2B: a supply-chain expert model (MetaFloor Manifest suite)},
author = {MetaFloor AI},
year = {2026},
howpublished = {\url{https://huggingface.co/metafloor-ai/manifest-orchestrator-2b}}
}<!-- manifest-suite:order -->