📄 Read the Whitepaper | 💬 Join the Community
Turns a hardware idea — a sentence, a short brief, even a sketch — into a complete build blueprint.
Tell it what to build — "a USB-powered desk lamp with touch dimming" — optionally with a short document or a concept image, and it returns one structured blueprint plan: the parts, the wiring, ordered build steps, a costed sourcing table, and an appearance spec with a ready-to-use image-generation prompt. It's a standalone, all-in-one model (no adapter upon request).
Early research preview. For drafting and exploring ideas — not a replacement for real engineering, CAD, or safety review.
Give it a hardware idea and it returns, as one machine-readable JSON object:
Your app can parse, check, and build on the result directly.
We test on requests the model has never seen during training. How often it produces a valid, well-structured blueprint:
| On held-out requests | Stock Qwen3.5-9B | Parti-Vision (free) | Parti-Vision (guided) |
|---|---|---|---|
| Valid, well-structured blueprint | FAIL | 67% | 83% |
On brand-new realistic requests, guided decoding reaches 97% valid blueprints (61% with free decoding); the stock base model manages FAIL on the same tests.
What's "guided decoding"? A standard serving option (guided_json in vLLM, "structured
outputs" in most hosted APIs) that constrains the output to your blueprint format. The model still
makes every design decision — the parts, the wiring, the steps, the costs — guided decoding just
guarantees the shape.
Any combination works; prompt + brief + render is strongest. The model reads text + images, so convert PDFs, LaTeX, CAD files, or spreadsheets to text or an image first.
The model answers in JSON directly — no reasoning preamble to strip.
from unsloth import FastVisionModel
REPO = "caid-technologies/parti-vision"
model, tok = FastVisionModel.from_pretrained(REPO, load_in_4bit=False)
FastVisionModel.for_inference(model)
SYSTEM_PROMPT = (
"You design maker/electronics products. Given a request, reply with one JSON object "
"describing the complete build — parts, wiring, build steps, sourcing, and appearance. "
"Output only the JSON."
)
messages = [
{"role": "system", "content": [{"type": "text", "text": SYSTEM_PROMPT}]},
{"role": "user", "content": [{"type": "text", "text": "Design a USB desk lamp with touch dimming."}]},
]
text = tok.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
inputs = tok(text=text, return_tensors="pt").to("cuda")
out = model.generate(**inputs, max_new_tokens=13000, do_sample=False, repetition_penalty=1.1)
print(tok.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
💡 Blueprints are long: keep max_new_tokens high and the repetition penalty on. To include an
image, add {"type": "image", "image": your_image} to the user content and pass images= to the
tokenizer.
🚀 Serving it for real? Use vLLM with guided_json (or your engine's structured-outputs mode)
constrained to your blueprint format — it takes valid-blueprint rates on unseen prompts from ~61%
to ~97%.
caid-technologies/parti-base,
the earlier 3B sibling.@misc{parti_vision_base,
title = {Parti-Vision},
author = {Caid Technologies},
year = {2026},
howpublished = {\url{https://huggingface.co/caid-technologies}}
}
model.safetensors-00003-of-00004.safetensors 5.4 GBmodel.safetensors-00002-of-00004.safetensors 5.3 GBmodel.safetensors-00001-of-00004.safetensors 5.3 GBmodel.safetensors-00004-of-00004.safetensors 3.3 GBQwen/Qwen3.5-9B