Instructions to use ajmaclin/prescription-donut-ocr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ajmaclin/prescription-donut-ocr with Transformers:

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

pipe = pipeline("image-text-to-text", model="ajmaclin/prescription-donut-ocr")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("ajmaclin/prescription-donut-ocr")
model = AutoModelForMultimodalLM.from_pretrained("ajmaclin/prescription-donut-ocr", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ajmaclin/prescription-donut-ocr with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ajmaclin/prescription-donut-ocr

SGLang

How to use ajmaclin/prescription-donut-ocr 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 "ajmaclin/prescription-donut-ocr" \
    --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": "ajmaclin/prescription-donut-ocr",
		"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 "ajmaclin/prescription-donut-ocr" \
        --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": "ajmaclin/prescription-donut-ocr",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ajmaclin/prescription-donut-ocr with Docker Model Runner:
```
docker model run hf.co/ajmaclin/prescription-donut-ocr
```

prescription-donut-ocr / checkpoint-10 /trainer_state.json

ajmaclin

Upload folder using huggingface_hub

9eb10cb verified 6 months ago

Raw

History Blame

1.33 kB

	{
	"best_metric": 6.029897689819336,
	"best_model_checkpoint": "/content/donut_finetuned/checkpoint-10",
	"epoch": 2.0,
	"eval_steps": 500,
	"global_step": 10,
	"is_hyper_param_search": false,
	"is_local_process_zero": true,
	"is_world_process_zero": true,
	"log_history": [
	{
	"epoch": 1.0,
	"eval_loss": 9.464871406555176,
	"eval_runtime": 4.0077,
	"eval_samples_per_second": 3.743,
	"eval_steps_per_second": 1.996,
	"step": 5
	},
	{
	"epoch": 2.0,
	"grad_norm": 46.585044860839844,
	"learning_rate": 2.4e-05,
	"loss": 10.4972,
	"step": 10
	},
	{
	"epoch": 2.0,
	"eval_loss": 6.029897689819336,
	"eval_runtime": 3.4276,
	"eval_samples_per_second": 4.376,
	"eval_steps_per_second": 2.334,
	"step": 10
	}
	],
	"logging_steps": 10,
	"max_steps": 100,
	"num_input_tokens_seen": 0,
	"num_train_epochs": 20,
	"save_steps": 500,
	"stateful_callbacks": {
	"TrainerControl": {
	"args": {
	"should_epoch_stop": false,
	"should_evaluate": false,
	"should_log": false,
	"should_save": true,
	"should_training_stop": false
	},
	"attributes": {}
	}
	},
	"total_flos": 5.00305864163328e+17,
	"train_batch_size": 2,
	"trial_name": null,
	"trial_params": null
	}