Instructions to use tedad09/PolizzeDonut-ConXLS-3Epochs-Da5PDF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tedad09/PolizzeDonut-ConXLS-3Epochs-Da5PDF with Transformers:

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

pipe = pipeline("image-text-to-text", model="tedad09/PolizzeDonut-ConXLS-3Epochs-Da5PDF")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("tedad09/PolizzeDonut-ConXLS-3Epochs-Da5PDF")
model = AutoModelForMultimodalLM.from_pretrained("tedad09/PolizzeDonut-ConXLS-3Epochs-Da5PDF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tedad09/PolizzeDonut-ConXLS-3Epochs-Da5PDF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tedad09/PolizzeDonut-ConXLS-3Epochs-Da5PDF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tedad09/PolizzeDonut-ConXLS-3Epochs-Da5PDF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/tedad09/PolizzeDonut-ConXLS-3Epochs-Da5PDF

SGLang

How to use tedad09/PolizzeDonut-ConXLS-3Epochs-Da5PDF 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 "tedad09/PolizzeDonut-ConXLS-3Epochs-Da5PDF" \
    --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": "tedad09/PolizzeDonut-ConXLS-3Epochs-Da5PDF",
		"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 "tedad09/PolizzeDonut-ConXLS-3Epochs-Da5PDF" \
        --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": "tedad09/PolizzeDonut-ConXLS-3Epochs-Da5PDF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use tedad09/PolizzeDonut-ConXLS-3Epochs-Da5PDF with Docker Model Runner:
```
docker model run hf.co/tedad09/PolizzeDonut-ConXLS-3Epochs-Da5PDF
```

PolizzeDonut-ConXLS-3Epochs-Da5PDF

This model is a fine-tuned version of tedad09/PolizzeDonut-SoloPDF-5Epochs on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.1339

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: 2e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.4146	1.0	26	0.1325
0.3395	2.0	52	0.1306
0.2623	3.0	78	0.1339

Framework versions

Transformers 4.38.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2

Downloads last month: 6

Safetensors

Model size

0.2B params

Tensor type

I64

F32

Inference Providers NEW

Image-Text-to-Text

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

Model tree for tedad09/PolizzeDonut-ConXLS-3Epochs-Da5PDF

Base model

naver-clova-ix/donut-base

Finetuned

tedad09/PolizzeDonut-SoloPDF-5Epochs

Finetuned

(1)

this model