Instructions to use yeelou/design2code-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use yeelou/design2code-hf with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="yeelou/design2code-hf", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("yeelou/design2code-hf", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use yeelou/design2code-hf with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "yeelou/design2code-hf" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "yeelou/design2code-hf", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/yeelou/design2code-hf
- SGLang
How to use yeelou/design2code-hf 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 "yeelou/design2code-hf" \ --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": "yeelou/design2code-hf", "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 "yeelou/design2code-hf" \ --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": "yeelou/design2code-hf", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use yeelou/design2code-hf with Docker Model Runner:
docker model run hf.co/yeelou/design2code-hf
Need some Help
I am currently exploring the "yeelou/design2code-hf-bit8" model for converting images to HTML. I appreciate the work that has gone into developing this model, and I am eager to understand its capabilities and integrate it into our projects. However, I have a few questions and would appreciate any guidance you can provide:
Documentation and Examples: Could you provide detailed documentation or examples on how to use the model effectively, including any specific preprocessing steps for the images?
Tokenization and Image Processing: Is there a specific tokenizer or image processor required for this model? If so, could you share guidance or references to the appropriate tools or libraries?
Model Capabilities: What types of images does the model work best with? Are there any limitations or specific use cases where the model might not perform well?
Performance Metrics: Are there any benchmarks or performance metrics available for this model? How does it compare to other similar models?
Community Engagement: Are there any ongoing or planned updates for this model? How can the community contribute to its development or improvement?
Thank you for your time and assistance. I look forward to your response and any insights you can provide to help us get the most out of this model