Instructions to use Humayoun/Donut5WithRandomPlacing with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Humayoun/Donut5WithRandomPlacing with Transformers:

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

pipe = pipeline("image-text-to-text", model="Humayoun/Donut5WithRandomPlacing")

# Load model directly
from transformers import AutoTokenizer, AutoModelForImageTextToText

tokenizer = AutoTokenizer.from_pretrained("Humayoun/Donut5WithRandomPlacing")
model = AutoModelForImageTextToText.from_pretrained("Humayoun/Donut5WithRandomPlacing")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Humayoun/Donut5WithRandomPlacing with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Humayoun/Donut5WithRandomPlacing"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Humayoun/Donut5WithRandomPlacing",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Humayoun/Donut5WithRandomPlacing

SGLang

How to use Humayoun/Donut5WithRandomPlacing 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 "Humayoun/Donut5WithRandomPlacing" \
    --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": "Humayoun/Donut5WithRandomPlacing",
		"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 "Humayoun/Donut5WithRandomPlacing" \
        --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": "Humayoun/Donut5WithRandomPlacing",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Humayoun/Donut5WithRandomPlacing with Docker Model Runner:
```
docker model run hf.co/Humayoun/Donut5WithRandomPlacing
```

Humayoun commited on Apr 4, 2023

Commit

276db14

1 Parent(s): 96f929a

Training in progress, epoch 15

Browse files

Files changed (2) hide show

pytorch_model.bin +1 -1
runs/Apr04_02-40-23_93603f7d305e/events.out.tfevents.1680576039.93603f7d305e.208.0 +2 -2

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae516ccd2fb009202c537b983d55b25b6106e20a77cf5390bdb77944fc08a526
 size 809350937

 version https://git-lfs.github.com/spec/v1
+oid sha256:bb5d755467b565c74110b83f3fd2d4c13d75e0e4ed0a84dab64708bb13c1e233
 size 809350937

runs/Apr04_02-40-23_93603f7d305e/events.out.tfevents.1680576039.93603f7d305e.208.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4af9735bcb6fa7302b6bdb5317e5c2271c7a1e75c9625e55efa2a392aceaba28
-size 10257

 version https://git-lfs.github.com/spec/v1
+oid sha256:dbbb33527768829c04176d9c34240bffaf04e46b70e5db747aef28afdbefb4e8
+size 10414