Instructions to use MrFitzmaurice/TrOCR-Lambda-Calculus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MrFitzmaurice/TrOCR-Lambda-Calculus with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="MrFitzmaurice/TrOCR-Lambda-Calculus")

# Load model directly
from transformers import AutoTokenizer, AutoModelForImageTextToText

tokenizer = AutoTokenizer.from_pretrained("MrFitzmaurice/TrOCR-Lambda-Calculus")
model = AutoModelForImageTextToText.from_pretrained("MrFitzmaurice/TrOCR-Lambda-Calculus")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MrFitzmaurice/TrOCR-Lambda-Calculus with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MrFitzmaurice/TrOCR-Lambda-Calculus"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MrFitzmaurice/TrOCR-Lambda-Calculus",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MrFitzmaurice/TrOCR-Lambda-Calculus

SGLang

How to use MrFitzmaurice/TrOCR-Lambda-Calculus 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 "MrFitzmaurice/TrOCR-Lambda-Calculus" \
    --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": "MrFitzmaurice/TrOCR-Lambda-Calculus",
		"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 "MrFitzmaurice/TrOCR-Lambda-Calculus" \
        --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": "MrFitzmaurice/TrOCR-Lambda-Calculus",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MrFitzmaurice/TrOCR-Lambda-Calculus with Docker Model Runner:
```
docker model run hf.co/MrFitzmaurice/TrOCR-Lambda-Calculus
```

This model aims to allow users to convert from handwritten text to lambda calculus code.

As far as I can tell, the idea of performing OCR on handwritten code has not been done before, likely due to the fact it is usually easier to type than write. However, with languages with extended character sets (lambda calculus, apl, lisp, etc.) it may be more useful to write out code and have it translated for you (especially for beginners).

This model specifically aims at lambda calculus.

Downloads last month: 8

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for MrFitzmaurice/TrOCR-Lambda-Calculus

Base model

microsoft/trocr-base-stage1

Finetuned

(19)

this model