Instructions to use ShuyiGuo/IS557_TrOCR_dutch with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ShuyiGuo/IS557_TrOCR_dutch with Transformers:

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

pipe = pipeline("image-text-to-text", model="ShuyiGuo/IS557_TrOCR_dutch")

# Load model directly
from transformers import AutoTokenizer, AutoModelForImageTextToText

tokenizer = AutoTokenizer.from_pretrained("ShuyiGuo/IS557_TrOCR_dutch")
model = AutoModelForImageTextToText.from_pretrained("ShuyiGuo/IS557_TrOCR_dutch")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ShuyiGuo/IS557_TrOCR_dutch with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ShuyiGuo/IS557_TrOCR_dutch"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ShuyiGuo/IS557_TrOCR_dutch",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ShuyiGuo/IS557_TrOCR_dutch

SGLang

How to use ShuyiGuo/IS557_TrOCR_dutch 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 "ShuyiGuo/IS557_TrOCR_dutch" \
    --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": "ShuyiGuo/IS557_TrOCR_dutch",
		"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 "ShuyiGuo/IS557_TrOCR_dutch" \
        --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": "ShuyiGuo/IS557_TrOCR_dutch",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ShuyiGuo/IS557_TrOCR_dutch with Docker Model Runner:
```
docker model run hf.co/ShuyiGuo/IS557_TrOCR_dutch
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

IS557_TrOCR_dutch

This model is a fine-tuned version of ShuyiGuo/IS557_TrOCR_AllData on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.0843
Cer: 0.1661

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
2.5052	0.3436	200	2.4755	0.4603
2.229	0.6873	400	2.0362	0.3556
1.4698	1.0309	600	1.6708	0.2893
1.1727	1.3746	800	1.4876	0.2616
1.3044	1.7182	1000	1.3246	0.2158
0.7114	2.0619	1200	1.1953	0.1867
0.6231	2.4055	1400	1.1291	0.1781
0.5886	2.7491	1600	1.0843	0.1661

Framework versions

Transformers 4.40.1
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1

Downloads last month: -

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

Model tree for ShuyiGuo/IS557_TrOCR_dutch

Base model

microsoft/trocr-base-stage1

Finetuned

ShuyiGuo/IS557_TrOCR_AllData

Finetuned

(1)

this model