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

Libraries

How to use AbnerYang/donut-model-noaug with Transformers:

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

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

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

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AbnerYang/donut-model-noaug with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AbnerYang/donut-model-noaug"
# 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-noaug",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

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

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

AbnerYang commited on Sep 4, 2023

Commit

d476cae

1 Parent(s): b5e8ec3

Training in progress, epoch 15

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:b73994dee1b91a90da4f4f82df7c6ba58cabe987db4c2901a0998ee891aa0e3b
 size 809419399

 version https://git-lfs.github.com/spec/v1
+oid sha256:7d8ef030e9598bb9da2c668f868736694362df1882a68c6c57244c5f0123daef
 size 809419399