---
license: apache-2.0
language:
  - en
tags:
  - blueprint
  - hardware
  - electronics
  - maker
  - text
  - mechanical
  - product-engineering
  - 3d
  - iot
  - robotics
  - cad

 
pipeline_tag: text-generation
base_model: Qwen/Qwen2.5-3B-Instruct
library_name: transformers
---

<div align="center">
  <img
    src="https://cdn-uploads.huggingface.co/production/uploads/65c5f5ba3f5ef63bb306ca94/D6qYJpAIDgaEAp5g39nrJ.jpeg"
    width="50%"
    alt="Parti-Base"
  >
  <h1>Parti Base</h1>
</div>

<hr>

<div align="center" style="line-height: 1;">
  <a href="https://huggingface.co/Qwen/Qwen2.5-3B-Instruct" target="_blank">
    <img alt="Base Model" src="https://img.shields.io/badge/Base_Model-Qwen2.5--3B-1e293b"/>
  </a>
  <a href="https://discord.gg/jHZCYFedP" target="_blank">
    <img alt="Discord" src="https://img.shields.io/badge/Discord-Join_the_community-5865F2?logo=discord&logoColor=white"/>
  </a>
</div>

<div align="center" style="line-height: 1;">
  <a href="https://huggingface.co/caid-technologies/parti-base/resolve/main/Parti-Base-Whitepaper.pdf" target="_blank">
    <img alt="Whitepaper" src="https://img.shields.io/badge/📄%20Whitepaper-PDF-475569"/>
  </a>
  <a href="https://www.apache.org/licenses/LICENSE-2.0" target="_blank">
    <img alt="License" src="https://img.shields.io/badge/License-Apache_2.0-0d9488"/>
  </a>
</div>

<p align="center">
  📄&nbsp;&nbsp;
  <a href="https://huggingface.co/caid-technologies/parti-base/resolve/main/Parti-Base-Whitepaper.pdf">
    <b>Read the Whitepaper</b>
  </a>
  &nbsp;&nbsp;|&nbsp;&nbsp;
  💬&nbsp;&nbsp;
  <a href="https://discord.gg/jHZCYFedP">Join the Community</a>
</p>

**Turns a plain-English hardware idea into an organized build plan.**

Tell it what to build — *"a compact desk clock with an e-ink display and an IR remote"* — and it
returns **one structured blueprint plan**: the parts, how they connect, ordered build steps, rough
sourcing and cost, and a quick design check. It's a **standalone, all-in-one model** (adapter-only
version upon request).

> **Early research preview.** For drafting and exploring ideas — not a replacement for real
> engineering, CAD, or safety review.

## What it does

Give it a hardware idea and it returns, as one machine-readable JSON object, any of:

- 📋 a **parts list**
- 🔌 a **wiring / connection map** between the parts
- 🛠️ ordered **build steps**
- 💲 rough **sourcing and cost**
- ✅ a basic **design check**
- 📦 or the **whole plan** at once

Ask for the complete plan, or just one piece (like only the parts list).

## Results

We test on projects it has **never seen during training**. How often it produces a valid,
well-structured result for each task:

| Task | Valid result |
|---|:--:|
| 🛠️ Build steps | ~100% |
| ✅ Design check | ~100% |
| 📋 Parts list | ~95% |
| 📦 Full project plan | ~85–97% |
| 🔌 Wiring map | ~67% |

It's strongest at **build steps, design checks, and parts lists**; full end-to-end plans are close
behind; **wiring maps are the hardest**. *Figures are from held-out testing and are being finalized
for the current version.*

Because it's a **small model**, treat the output as a helpful **first draft to review**, not a
finished design.

## Where it fits

- **Reliable structured JSON from plain English on a small (3B) model** that runs on modest
  hardware.
- For **images** (sketches / renders), **improved quality**, and **larger projects**, use [`parti-vision`](https://huggingface.co/caid-technologies/parti-vision) (9B, multimodal).

## What you can give it

- **A plain-English request** — one or two sentences. **Text only**

## Try it

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

REPO = "caid-technologies/parti-base"
model = AutoModelForCausalLM.from_pretrained(REPO, device_map="auto", torch_dtype="bfloat16")
tok = AutoTokenizer.from_pretrained(REPO)

msgs = [
    {"role": "system", "content":
        "You design maker/electronics products. Given a request, reply with a single JSON object "
        "describing the complete build plan. Output only the JSON."},
    {"role": "user", "content": "A compact desk clock with an e-ink display and an IR remote."},
]
inputs = tok.apply_chat_template(
    msgs, add_generation_prompt=True, return_tensors="pt", return_dict=True).to(model.device)
out = model.generate(**inputs, max_new_tokens=6144, do_sample=False,
                     repetition_penalty=1.1, pad_token_id=tok.eos_token_id)
print(tok.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
```

💡 **Tips:** keep `do_sample=False` (greedy — sampling degrades the JSON), keep
`max_new_tokens` high (≥ 6000) so long plans aren't cut off, and keep `repetition_penalty=1.1` so
wiring lists don't get stuck repeating. For Ollama / local apps, convert to GGUF with llama.cpp.

## Good to know

- It's a **small model**, so complex, many-part projects are harder for it.
- It **proposes** designs; it doesn't verify them. Always sanity-check before building.
- It's strongest on common project types (lab tools, smart-home) and weaker on rarer ones.

## Learn more

- 📄 **[Technical whitepaper (PDF)](https://huggingface.co/caid-technologies/parti-base/resolve/main/Parti-Base-Whitepaper.pdf)** —
  what it does, training approach, evaluation methodology, and per-task results.
- 💬 **[Discord community](https://discord.gg/jHZCYFedP)** — questions, builds, feedback.
- 🚀 **Want images and higher quality?** See [`caid-technologies/parti-vision`](https://huggingface.co/caid-technologies/parti-vision),
  the 9B multimodal model.

## Citation

```bibtex
@misc{parti_base,
  title  = {Parti-Base},
  author = {Caid Technologies},
  year   = {2026},
  howpublished = {\url{https://huggingface.co/caid-technologies}}
}
```