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

Libraries

How to use Humayoun/ThesisDonut with Transformers:

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

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

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

tokenizer = AutoTokenizer.from_pretrained("Humayoun/ThesisDonut")
model = AutoModelForMultimodalLM.from_pretrained("Humayoun/ThesisDonut", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Humayoun/ThesisDonut with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Humayoun/ThesisDonut

SGLang

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

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

Humayoun commited on May 14, 2023

Commit

e682e28

1 Parent(s): 688c443

Training in progress, epoch 4

Browse files

Files changed (2) hide show

pytorch_model.bin +1 -1
runs/May14_13-53-01_db8ce5e3c020/events.out.tfevents.1684072385.db8ce5e3c020.6613.11 +2 -2

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:267d64075c9b30d40e864ae01dbafa1572d3290369aa1d135d4aca4f39e45c62
 size 809309977

 version https://git-lfs.github.com/spec/v1
+oid sha256:0a0cf520320ed59a650632939c76e3dbc66f59d28735aeac3f9ddd297f94e932
 size 809309977

runs/May14_13-53-01_db8ce5e3c020/events.out.tfevents.1684072385.db8ce5e3c020.6613.11 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c6db744f2229fb6f98f9d2a08fe22385c2a7907c6d2f65360d2ca89ca6de246
-size 9799

 version https://git-lfs.github.com/spec/v1
+oid sha256:bc12382eda55d290220daafb5578d57f655f90adfff9ba2206693aa06bed6fef
+size 10113