Instructions to use us4/trocr-mathwriting with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use us4/trocr-mathwriting with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="us4/trocr-mathwriting")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("us4/trocr-mathwriting") model = AutoModelForMultimodalLM.from_pretrained("us4/trocr-mathwriting", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use us4/trocr-mathwriting with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "us4/trocr-mathwriting" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "us4/trocr-mathwriting", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/us4/trocr-mathwriting
- SGLang
How to use us4/trocr-mathwriting 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 "us4/trocr-mathwriting" \ --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": "us4/trocr-mathwriting", "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 "us4/trocr-mathwriting" \ --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": "us4/trocr-mathwriting", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use us4/trocr-mathwriting with Docker Model Runner:
docker model run hf.co/us4/trocr-mathwriting
- Xet hash:
- 8e9e1e4fa33d6aa02666903e8e43c0bfb7b3b1b803e9300a16d2f4b6ea8f00c5
- Size of remote file:
- 4.46 GB
- SHA256:
- 11422caeecd3350c5b6d88d85b88c925c005c063939d46afa6e2023f32caae01
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.