Instructions to use campedersen/cad0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use campedersen/cad0 with Transformers:

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

pipe = pipeline("text-generation", model="campedersen/cad0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("campedersen/cad0")
model = AutoModelForCausalLM.from_pretrained("campedersen/cad0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use campedersen/cad0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "campedersen/cad0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "campedersen/cad0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/campedersen/cad0

SGLang

How to use campedersen/cad0 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 "campedersen/cad0" \
    --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": "campedersen/cad0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "campedersen/cad0" \
        --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": "campedersen/cad0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use campedersen/cad0 with Docker Model Runner:
```
docker model run hf.co/campedersen/cad0
```

campedersen commited on Feb 4

Commit

0c3d85d

verified ·

1 Parent(s): 6ffb5b8

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -18,7 +18,7 @@ pipeline_tag: text-generation
 **cad0** is a fine-tuned language model for text-to-CAD generation. Given a natural
 language description of a mechanical part, it generates [Compact
-IR](https://github.com/campedersen/vcad) — a token-efficient domain-specific
 language for parametric 3D geometry.
 ## Demo
@@ -41,7 +41,7 @@ Output: C 50 30 5
 ```
 The Compact IR output can be parsed and evaluated by the [vcad
-kernel](https://github.com/campedersen/vcad) to produce editable parametric
 geometry.
 ## Supported Part Types
@@ -181,7 +181,7 @@ workarounds
 ## Related
-- https://github.com/campedersen/vcad — Open-source parametric CAD with custom BRep
 kernel
 - https://vcad.io — Web app with cad0 integration
 - https://huggingface.co/campedersen/cad0-mini — 0.5B distilled model for browser

 **cad0** is a fine-tuned language model for text-to-CAD generation. Given a natural
 language description of a mechanical part, it generates [Compact
+IR](https://github.com/ecto/vcad) — a token-efficient domain-specific
 language for parametric 3D geometry.
 ## Demo
 ```
 The Compact IR output can be parsed and evaluated by the [vcad
+kernel](https://github.com/ecto/vcad) to produce editable parametric
 geometry.
 ## Supported Part Types
 ## Related
+- https://github.com/ecto/vcad — Open-source parametric CAD with custom BRep
 kernel
 - https://vcad.io — Web app with cad0 integration
 - https://huggingface.co/campedersen/cad0-mini — 0.5B distilled model for browser