Instructions to use ivelin/donut-refexp-combined-v1-backup with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ivelin/donut-refexp-combined-v1-backup with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="ivelin/donut-refexp-combined-v1-backup")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("ivelin/donut-refexp-combined-v1-backup") model = AutoModelForMultimodalLM.from_pretrained("ivelin/donut-refexp-combined-v1-backup", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use ivelin/donut-refexp-combined-v1-backup with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ivelin/donut-refexp-combined-v1-backup" # 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-combined-v1-backup", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ivelin/donut-refexp-combined-v1-backup
- SGLang
How to use ivelin/donut-refexp-combined-v1-backup 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-combined-v1-backup" \ --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-combined-v1-backup", "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-combined-v1-backup" \ --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-combined-v1-backup", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ivelin/donut-refexp-combined-v1-backup with Docker Model Runner:
docker model run hf.co/ivelin/donut-refexp-combined-v1-backup
Commit History
-
Upload processor
6f1f7e2 -
Upload processor
4b69672
-
Upload processor
e511dff
-
Upload processor
e86622a
-
Upload processor
4105e9d -
Upload processor
167ba10
-
Upload processor
3e615bb -
Upload processor
65752f4 -
Upload processor
c8428b4 -
Upload processor
cfa6b62 -
Upload processor
895395e -
Upload processor
0e8079d
-
Upload processor
414de34 -
Upload processor
aae50a3
-
Upload processor
2676248 -
Upload processor
937b9a6
-
Upload processor
baca096 -
Upload processor
1c0ed32
-
Upload processor
bbd2857 -
Upload processor
81849e0 -
Upload processor
d8c7771 -
Upload processor
e1d10c4
-
Upload processor
5afc96b -
Upload processor
bd62133 -
Upload processor
643d963 -
Upload processor
4f25ad2
-
Upload processor
e5808d9 -
Upload processor
435913b -
Upload processor
10bb846 -
Upload processor
6ae6001 -
Upload processor
8b4b124 -
Upload processor
bc30774 -
Upload processor
3797496
-
Upload processor
3655043 -
Upload processor
5fdeab0
-
Upload processor
03e10f7 -
Upload processor
4d37f8d
-
Upload processor
e37cb81