Instructions to use hpge9/donut-base-ticket with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hpge9/donut-base-ticket with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="hpge9/donut-base-ticket")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("hpge9/donut-base-ticket") model = AutoModelForMultimodalLM.from_pretrained("hpge9/donut-base-ticket") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use hpge9/donut-base-ticket with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "hpge9/donut-base-ticket" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hpge9/donut-base-ticket", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/hpge9/donut-base-ticket
- SGLang
How to use hpge9/donut-base-ticket 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 "hpge9/donut-base-ticket" \ --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": "hpge9/donut-base-ticket", "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 "hpge9/donut-base-ticket" \ --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": "hpge9/donut-base-ticket", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use hpge9/donut-base-ticket with Docker Model Runner:
docker model run hf.co/hpge9/donut-base-ticket
Update preprocessor_config.json
Browse files- preprocessor_config.json +1 -2
preprocessor_config.json
CHANGED
|
@@ -5,12 +5,12 @@
|
|
| 5 |
"do_rescale": true,
|
| 6 |
"do_resize": true,
|
| 7 |
"do_thumbnail": true,
|
|
|
|
| 8 |
"image_mean": [
|
| 9 |
0.5,
|
| 10 |
0.5,
|
| 11 |
0.5
|
| 12 |
],
|
| 13 |
-
"image_processor_type": "DonutImageProcessor",
|
| 14 |
"image_std": [
|
| 15 |
0.5,
|
| 16 |
0.5,
|
|
@@ -18,7 +18,6 @@
|
|
| 18 |
],
|
| 19 |
"processor_class": "DonutProcessor",
|
| 20 |
"resample": 2,
|
| 21 |
-
"rescale_factor": 0.00392156862745098,
|
| 22 |
"size": [
|
| 23 |
1920,
|
| 24 |
2560
|
|
|
|
| 5 |
"do_rescale": true,
|
| 6 |
"do_resize": true,
|
| 7 |
"do_thumbnail": true,
|
| 8 |
+
"feature_extractor_type": "DonutFeatureExtractor",
|
| 9 |
"image_mean": [
|
| 10 |
0.5,
|
| 11 |
0.5,
|
| 12 |
0.5
|
| 13 |
],
|
|
|
|
| 14 |
"image_std": [
|
| 15 |
0.5,
|
| 16 |
0.5,
|
|
|
|
| 18 |
],
|
| 19 |
"processor_class": "DonutProcessor",
|
| 20 |
"resample": 2,
|
|
|
|
| 21 |
"size": [
|
| 22 |
1920,
|
| 23 |
2560
|