Instructions to use BadreddineHug/donut-base-ocr8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BadreddineHug/donut-base-ocr8 with Transformers:

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

pipe = pipeline("image-text-to-text", model="BadreddineHug/donut-base-ocr8")

# Load model directly
from transformers import AutoTokenizer, AutoModelForImageTextToText

tokenizer = AutoTokenizer.from_pretrained("BadreddineHug/donut-base-ocr8")
model = AutoModelForImageTextToText.from_pretrained("BadreddineHug/donut-base-ocr8")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use BadreddineHug/donut-base-ocr8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BadreddineHug/donut-base-ocr8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BadreddineHug/donut-base-ocr8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/BadreddineHug/donut-base-ocr8

SGLang

How to use BadreddineHug/donut-base-ocr8 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 "BadreddineHug/donut-base-ocr8" \
    --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": "BadreddineHug/donut-base-ocr8",
		"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 "BadreddineHug/donut-base-ocr8" \
        --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": "BadreddineHug/donut-base-ocr8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use BadreddineHug/donut-base-ocr8 with Docker Model Runner:
```
docker model run hf.co/BadreddineHug/donut-base-ocr8
```

BadreddineHug commited on Jul 6, 2023

Commit

cc521b2

1 Parent(s): 8499eb3

Training in progress, epoch 3

Browse files

Files changed (2) hide show

pytorch_model.bin +1 -1
runs/Jul06_11-39-17_28e44081c9f5/events.out.tfevents.1688643564.28e44081c9f5.1262.0 +2 -2

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de3966f4e598c7747b35789b6f548b75ab25ccdf4c02924288d5e0c298a64662
 size 809293593

 version https://git-lfs.github.com/spec/v1
+oid sha256:26ef50c99857bfaa3be4be9f59dda44f51040c63e8dbea44b87cb80fe4f6a3d4
 size 809293593

runs/Jul06_11-39-17_28e44081c9f5/events.out.tfevents.1688643564.28e44081c9f5.1262.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77e18b8c92cc5d5e5ea58b91ac88090c7973fb5939970965d97d647fa7fad664
-size 15633

 version https://git-lfs.github.com/spec/v1
+oid sha256:e17451842c1a32cef21b983dd51de9561e3a1af0a10ddeef87267a47a98aa9d8
+size 19175