Instructions to use khhuang/chart-to-table with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use khhuang/chart-to-table with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="khhuang/chart-to-table")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("khhuang/chart-to-table") model = AutoModelForMultimodalLM.from_pretrained("khhuang/chart-to-table", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use khhuang/chart-to-table with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "khhuang/chart-to-table" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "khhuang/chart-to-table", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/khhuang/chart-to-table
- SGLang
How to use khhuang/chart-to-table 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 "khhuang/chart-to-table" \ --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": "khhuang/chart-to-table", "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 "khhuang/chart-to-table" \ --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": "khhuang/chart-to-table", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use khhuang/chart-to-table with Docker Model Runner:
docker model run hf.co/khhuang/chart-to-table
Commit History
update model weights 04496bf
khuangaf commited on
update readme a2c7451
khuangaf commited on
update readme 128d177
khuangaf commited on
update readme 039dd31
khuangaf commited on
upload model 4eed8c5
khuangaf commited on
update readme 87feab4
khuangaf commited on
initial commit ccd9308
Kung-Hsiang Huang commited on