Text Generation
Transformers
Safetensors
llama
code-generation
plantuml
text-to-code
text-generation-inference
How to use from
SGLangUse 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 "MohamedIFQ/sysmlAI" \
--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": "MohamedIFQ/sysmlAI",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'Quick Links
SysML AI: PlantUML Code Generator
This model is a fine-tuned version of [Base Model Name] (e.g., GPT-2, CodeGen, etc.) that generates PlantUML code from natural language descriptions. It can be used to create sequence diagrams, class diagrams, and other PlantUML diagrams, making it a valuable tool for software engineers, system architects, and anyone who needs to visualize system designs.
Model Description
- Architecture: [Describe the base model architecture, e.g., Transformer with X layers, Y attention heads]
- Fine-tuning Dataset: [Specify the dataset used for fine-tuning, including the number of examples, source, and data format]
- Training Objective: [Describe the training objective, e.g., minimizing cross-entropy loss between predicted and actual PlantUML tokens]
- Evaluation Metrics: [List the metrics used to evaluate the model, e.g., BLEU score, ROUGE score, or other relevant code generation metrics]
Intended Uses & Limitations
- Intended Use: Generating PlantUML code from natural language descriptions to aid in system design and visualization.
- Limitations:
- May not handle complex or ambiguous descriptions accurately.
- May require some manual editing of the generated code for optimal results.
- Performance may vary depending on the complexity of the desired diagram.
How to Use
Installation:
- Downloads last month
- 6
Install from pip and serve model
# Install SGLang from pip: pip install sglang# Start the SGLang server: python3 -m sglang.launch_server \ --model-path "MohamedIFQ/sysmlAI" \ --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": "MohamedIFQ/sysmlAI", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'