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

Libraries

How to use ivelin/donut-refexp-draft with Transformers:

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

pipe = pipeline("image-text-to-text", model="ivelin/donut-refexp-draft")

# Load model directly
from transformers import AutoTokenizer, AutoModelForImageTextToText

tokenizer = AutoTokenizer.from_pretrained("ivelin/donut-refexp-draft")
model = AutoModelForImageTextToText.from_pretrained("ivelin/donut-refexp-draft")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ivelin/donut-refexp-draft with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ivelin/donut-refexp-draft

SGLang

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

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

ivelin commited on Jan 11, 2023

Commit

82c0440

1 Parent(s): 9f3ce5a

Upload model

Browse files

Files changed (2) hide show

config.json +1 -1
pytorch_model.bin +1 -1

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_commit_hash": "5e10164fade1d472d8faa21916c25f38cc4bf37d",
   "_name_or_path": "ivelin/donut-refexp-draft",
   "architectures": [
     "VisionEncoderDecoderModel"

 {
+  "_commit_hash": "d3fe79ba3245dd0826bd359c66a7f000bed21055",
   "_name_or_path": "ivelin/donut-refexp-draft",
   "architectures": [
     "VisionEncoderDecoderModel"

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef2391dca76f51979efd1b19b6fbda4a297c0f984e532fa5ed9aaf3bc545625e
 size 809233625

 version https://git-lfs.github.com/spec/v1
+oid sha256:7530ca8562c106f87a69da7dca15e20853892f4fe2d86c15a7f354f7c82f8a12
 size 809233625