Instructions to use caid-technologies/parti-vision with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use caid-technologies/parti-vision with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="caid-technologies/parti-vision")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("caid-technologies/parti-vision")
model = AutoModelForMultimodalLM.from_pretrained("caid-technologies/parti-vision", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use caid-technologies/parti-vision with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "caid-technologies/parti-vision"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "caid-technologies/parti-vision",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/caid-technologies/parti-vision

SGLang

How to use caid-technologies/parti-vision with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "caid-technologies/parti-vision" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "caid-technologies/parti-vision",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "caid-technologies/parti-vision" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "caid-technologies/parti-vision",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use caid-technologies/parti-vision with Docker Model Runner:
```
docker model run hf.co/caid-technologies/parti-vision
```

L0k1 commited on Jul 27

Commit

4faacb2

verified ·

1 Parent(s): 8e5a711

Model card: remove docs/assets image embeds (not present in HF repo, rendered broken)

Browse files

Files changed (1) hide show

README.md +2 -8

README.md CHANGED Viewed

@@ -19,31 +19,25 @@ base_model_relation: finetune
 library_name: transformers
 ---
-# Parti-Vision
 [![Discord](https://img.shields.io/badge/Discord-join_the_community-5865F2?logo=discord&logoColor=white)](https://discord.gg/jHZCYFedP)
 [![License](https://img.shields.io/badge/License-Apache_2.0-0d9488)](https://www.apache.org/licenses/LICENSE-2.0)
-[![Model](https://img.shields.io/badge/Base-Qwen3.5--9B-1e293b)](https://huggingface.co/Qwen/Qwen3.5-9B)
 [![Whitepaper](https://img.shields.io/badge/📄_Whitepaper-PDF-475569)](docs/whitepaper/Parti-Vision-Whitepaper.pdf)
 **Parti-Vision turns a hardware idea — a sentence, a short brief, even a sketch — into a complete build blueprint.**
-![A hand-drawn desk lamp sketch turned into a finished product render](docs/assets/hero_pair.jpg)
 Tell it what to build — *"a USB-powered desk lamp with touch dimming"* — and it returns one JSON
 blueprint: parts list, pin-level 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**. By [caid-technologies](https://huggingface.co/caid-technologies).
-![Three steps: describe or sketch it, Parti-Vision designs it, get a build blueprint](docs/assets/how_it_works.png)
 > **Early research preview.** For drafting and exploring ideas — not a replacement for real
 > engineering, CAD, or safety review.
 ## Does it actually work?
-![Valid blueprints on new realistic requests: stock Qwen 0%, Parti-Vision 61%, with guided decoding 97%](docs/assets/metric_headline.png)
 On brand-new realistic requests, **97% of outputs are valid, machine-checkable blueprints** when
 served with guided decoding (61% with plain decoding; the stock base model: 0%). On held-out
 training-style prompts: 83% guided / 67% free.

 library_name: transformers
 ---
+# Parti-Vision Base — Qwen3.5-9B
 [![Discord](https://img.shields.io/badge/Discord-join_the_community-5865F2?logo=discord&logoColor=white)](https://discord.gg/jHZCYFedP)
 [![License](https://img.shields.io/badge/License-Apache_2.0-0d9488)](https://www.apache.org/licenses/LICENSE-2.0)
+[![Base](https://img.shields.io/badge/Base-Qwen3.5--9B-1e293b)](https://huggingface.co/Qwen/Qwen3.5-9B)
 [![Whitepaper](https://img.shields.io/badge/📄_Whitepaper-PDF-475569)](docs/whitepaper/Parti-Vision-Whitepaper.pdf)
 **Parti-Vision 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"* — and it returns one JSON
 blueprint: parts list, pin-level 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**. By [caid-technologies](https://huggingface.co/caid-technologies).
 > **Early research preview.** For drafting and exploring ideas — not a replacement for real
 > engineering, CAD, or safety review.
 ## Does it actually work?
 On brand-new realistic requests, **97% of outputs are valid, machine-checkable blueprints** when
 served with guided decoding (61% with plain decoding; the stock base model: 0%). On held-out
 training-style prompts: 83% guided / 67% free.