Instructions to use maxall4/TrOCR-biochemistry with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use maxall4/TrOCR-biochemistry with Transformers:

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

pipe = pipeline("image-text-to-text", model="maxall4/TrOCR-biochemistry")

# Load model directly
from transformers import AutoTokenizer, AutoModelForImageTextToText

tokenizer = AutoTokenizer.from_pretrained("maxall4/TrOCR-biochemistry")
model = AutoModelForImageTextToText.from_pretrained("maxall4/TrOCR-biochemistry")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use maxall4/TrOCR-biochemistry with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "maxall4/TrOCR-biochemistry"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "maxall4/TrOCR-biochemistry",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/maxall4/TrOCR-biochemistry

SGLang

How to use maxall4/TrOCR-biochemistry 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 "maxall4/TrOCR-biochemistry" \
    --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": "maxall4/TrOCR-biochemistry",
		"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 "maxall4/TrOCR-biochemistry" \
        --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": "maxall4/TrOCR-biochemistry",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use maxall4/TrOCR-biochemistry with Docker Model Runner:
```
docker model run hf.co/maxall4/TrOCR-biochemistry
```

TrOCR Biochemistry

This is a finetuned model based on the TrOCR model. It was finetuned on the biochemistry-ocr dataset to make the model better at recognizing text like Kcat/Km, Ki, Km, chemical names and greek symbols.

Usage

This model can be used just lile TrOCR just change the model name to maxall4/TrOCR-biochemistry. You can find the TrOCR docs here.

Example:

from transformers import TrOCRProcessor, VisionEncoderDecoderModel
import requests
from PIL import Image

processor = TrOCRProcessor.from_pretrained("microsoft/trocr-base-handwritten")
model = VisionEncoderDecoderModel.from_pretrained("maxall4/TrOCR-biochemistry")

image = Image.open('kikcat.png').convert("RGB")

pixel_values = processor(image, return_tensors="pt").pixel_values
generated_ids = model.generate(pixel_values)

generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(generated_text)

Downloads last month: 8

Safetensors

Model size

0.4B params

Tensor type

F32

Inference Providers NEW

Image-Text-to-Text

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

maxall4
/

TrOCR-biochemistry

TrOCR Biochemistry

Usage

Dataset used to train maxall4/TrOCR-biochemistry