Text Generation
Transformers
Safetensors
designcoder
ui-generation
front-end
html
css
javascript
code-generation
full-sft
Instructions to use xingxm/DesignCoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use xingxm/DesignCoder with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="xingxm/DesignCoder")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("xingxm/DesignCoder", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use xingxm/DesignCoder with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "xingxm/DesignCoder" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "xingxm/DesignCoder", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/xingxm/DesignCoder
- SGLang
How to use xingxm/DesignCoder 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 "xingxm/DesignCoder" \ --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": "xingxm/DesignCoder", "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 "xingxm/DesignCoder" \ --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": "xingxm/DesignCoder", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use xingxm/DesignCoder with Docker Model Runner:
docker model run hf.co/xingxm/DesignCoder
Download eval/api_baselines_200/scores_summary.json from xingxm/DesignCoder: direct link, hf CLI and curl.
- Browser
- Download file 2.8 kB
-
https://huggingface.co/xingxm/DesignCoder/resolve/main/eval/api_baselines_200/scores_summary.json
- Command line
-
hf download hf://xingxm/DesignCoder/eval/api_baselines_200/scores_summary.json
-
curl -L -o scores_summary.json https://huggingface.co/xingxm/DesignCoder/resolve/main/eval/api_baselines_200/scores_summary.json
2.8 kB
| { | |
| "summary": { | |
| "api_azure_openai_gpt-5.2": { | |
| "label": "GPT-5.2", | |
| "n_cases": 200, | |
| "n_generated": 200, | |
| "overall": 89.9, | |
| "overall_no_vsd": 88.38, | |
| "prompt_fit": 88.33, | |
| "frozen": 86.37, | |
| "overall_landing": 92.09, | |
| "n_landing": 130, | |
| "overall_dashboard": 85.83, | |
| "n_dashboard": 70, | |
| "overall_track_A": 89.64, | |
| "overall_track_B": 90.51 | |
| }, | |
| "claude-opus-4-6-v1": { | |
| "label": "Claude Opus 4.6", | |
| "n_cases": 200, | |
| "n_generated": 200, | |
| "overall": 86.91, | |
| "overall_no_vsd": 84.9, | |
| "prompt_fit": 73.38, | |
| "frozen": 73.01, | |
| "overall_landing": 82.86, | |
| "n_landing": 130, | |
| "overall_dashboard": 94.42, | |
| "n_dashboard": 70, | |
| "overall_track_A": 85.74, | |
| "overall_track_B": 89.64 | |
| }, | |
| "claude-sonnet-4.6": { | |
| "label": "Claude Sonnet 4.6", | |
| "n_cases": 200, | |
| "n_generated": 200, | |
| "overall": 86.12, | |
| "overall_no_vsd": 83.98, | |
| "prompt_fit": 68.9, | |
| "frozen": 67.66, | |
| "overall_landing": 82.62, | |
| "n_landing": 130, | |
| "overall_dashboard": 92.61, | |
| "n_dashboard": 70, | |
| "overall_track_A": 85.09, | |
| "overall_track_B": 88.51 | |
| }, | |
| "deepseek-v4-flash": { | |
| "label": "DeepSeek-V4 Flash", | |
| "n_cases": 200, | |
| "n_generated": 200, | |
| "overall": 89.17, | |
| "overall_no_vsd": 87.4, | |
| "prompt_fit": 74.17, | |
| "frozen": 71.77, | |
| "overall_landing": 86.52, | |
| "n_landing": 130, | |
| "overall_dashboard": 94.1, | |
| "n_dashboard": 70, | |
| "overall_track_A": 88.82, | |
| "overall_track_B": 89.99 | |
| }, | |
| "deepseek-v4-pro": { | |
| "label": "DeepSeek-V4 Pro", | |
| "n_cases": 200, | |
| "n_generated": 200, | |
| "overall": 88.89, | |
| "overall_no_vsd": 87.19, | |
| "prompt_fit": 78.03, | |
| "frozen": 78.52, | |
| "overall_landing": 87.45, | |
| "n_landing": 130, | |
| "overall_dashboard": 91.56, | |
| "n_dashboard": 70, | |
| "overall_track_A": 88.14, | |
| "overall_track_B": 90.64 | |
| }, | |
| "glm-5.1": { | |
| "label": "GLM-5.1", | |
| "n_cases": 200, | |
| "n_generated": 200, | |
| "overall": 79.66, | |
| "overall_no_vsd": 76.77, | |
| "prompt_fit": 59.69, | |
| "frozen": 60.7, | |
| "overall_landing": 75.23, | |
| "n_landing": 130, | |
| "overall_dashboard": 87.91, | |
| "n_dashboard": 70, | |
| "overall_track_A": 76.77, | |
| "overall_track_B": 86.41 | |
| }, | |
| "kimi-k2.6": { | |
| "label": "Kimi-K2.6", | |
| "n_cases": 200, | |
| "n_generated": 200, | |
| "overall": 79.58, | |
| "overall_no_vsd": 76.55, | |
| "prompt_fit": 57.61, | |
| "frozen": 56.94, | |
| "overall_landing": 74.99, | |
| "n_landing": 130, | |
| "overall_dashboard": 88.1, | |
| "n_dashboard": 70, | |
| "overall_track_A": 78.18, | |
| "overall_track_B": 82.83 | |
| } | |
| }, | |
| "n_rows": 1400 | |
| } |