Instructions to use AbnerYang/donut-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AbnerYang/donut-model with Transformers:

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

pipe = pipeline("image-text-to-text", model="AbnerYang/donut-model")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("AbnerYang/donut-model")
model = AutoModelForMultimodalLM.from_pretrained("AbnerYang/donut-model", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AbnerYang/donut-model with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AbnerYang/donut-model

SGLang

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

Docker Model Runner
How to use AbnerYang/donut-model with Docker Model Runner:
```
docker model run hf.co/AbnerYang/donut-model
```

AbnerYang commited on Sep 4, 2023

Commit

446e0e0

1 Parent(s): 99f22f5

Training in progress, epoch 7

Browse files

Files changed (1) hide show

pytorch_model.bin +1 -1

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bc9b5fed0cf3ef97e654842d228891c12558c2cc9f12ba67b34ec0978af111e
 size 809408891

 version https://git-lfs.github.com/spec/v1
+oid sha256:6edcb2fc05afc8d83d2bde4c03dea56ee3db36c49deebf985b8dd412fd46a32b
 size 809408891