Text Generation
Transformers
Safetensors
English
cad
cadquery
3d-modeling
code-generation
mechanical-engineering
text-to-cad
geometry
python
gemma
fine-tuned
Eval Results (legacy)
Instructions to use numinousmuses/C3D-v0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use numinousmuses/C3D-v0 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="numinousmuses/C3D-v0")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("numinousmuses/C3D-v0", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use numinousmuses/C3D-v0 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "numinousmuses/C3D-v0" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "numinousmuses/C3D-v0", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/numinousmuses/C3D-v0
- SGLang
How to use numinousmuses/C3D-v0 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 "numinousmuses/C3D-v0" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "numinousmuses/C3D-v0", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "numinousmuses/C3D-v0" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "numinousmuses/C3D-v0", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use numinousmuses/C3D-v0 with Docker Model Runner:
docker model run hf.co/numinousmuses/C3D-v0
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# C3D-v0: AI-Powered CAD Code Generation Model
|
| 2 |
|
| 3 |
**Fine-tuned Gemma 3n model for generating CADQuery Python code from natural language descriptions**
|
|
@@ -173,7 +218,7 @@ result = gear
|
|
| 173 |
|
| 174 |
## License
|
| 175 |
|
| 176 |
-
|
| 177 |
|
| 178 |
---
|
| 179 |
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
library_name: transformers
|
| 6 |
+
tags:
|
| 7 |
+
- cad
|
| 8 |
+
- cadquery
|
| 9 |
+
- 3d-modeling
|
| 10 |
+
- code-generation
|
| 11 |
+
- mechanical-engineering
|
| 12 |
+
- text-to-cad
|
| 13 |
+
- geometry
|
| 14 |
+
- python
|
| 15 |
+
- gemma
|
| 16 |
+
- fine-tuned
|
| 17 |
+
pipeline_tag: text-generation
|
| 18 |
+
base_model: unsloth/gemma-3n-E4B-it
|
| 19 |
+
datasets:
|
| 20 |
+
- text-to-cadquery
|
| 21 |
+
widget:
|
| 22 |
+
- text: "Create a simple gear with 12 teeth"
|
| 23 |
+
example_title: "Gear Generation"
|
| 24 |
+
- text: "Generate a phone case for iPhone 15"
|
| 25 |
+
example_title: "Phone Case"
|
| 26 |
+
- text: "Make a rectangular bracket with mounting holes"
|
| 27 |
+
example_title: "Bracket Design"
|
| 28 |
+
- text: "Design a simple pulley with a 50mm diameter"
|
| 29 |
+
example_title: "Pulley Design"
|
| 30 |
+
model-index:
|
| 31 |
+
- name: C3D-v0
|
| 32 |
+
results:
|
| 33 |
+
- task:
|
| 34 |
+
type: text-generation
|
| 35 |
+
name: CAD Code Generation
|
| 36 |
+
dataset:
|
| 37 |
+
name: text-to-cadquery
|
| 38 |
+
type: text-to-cadquery
|
| 39 |
+
metrics:
|
| 40 |
+
- name: Code Execution Success Rate
|
| 41 |
+
type: execution_success
|
| 42 |
+
value: "High"
|
| 43 |
+
verified: false
|
| 44 |
+
---
|
| 45 |
+
|
| 46 |
# C3D-v0: AI-Powered CAD Code Generation Model
|
| 47 |
|
| 48 |
**Fine-tuned Gemma 3n model for generating CADQuery Python code from natural language descriptions**
|
|
|
|
| 218 |
|
| 219 |
## License
|
| 220 |
|
| 221 |
+
This model inherits the license from the base Gemma 3n model. Please refer to the original Gemma license for usage terms.
|
| 222 |
|
| 223 |
---
|
| 224 |
|