Instructions to use AiDevelopment/donut-base-sroie with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AiDevelopment/donut-base-sroie with Transformers:

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

pipe = pipeline("image-text-to-text", model="AiDevelopment/donut-base-sroie")

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

tokenizer = AutoTokenizer.from_pretrained("AiDevelopment/donut-base-sroie")
model = AutoModelForMultimodalLM.from_pretrained("AiDevelopment/donut-base-sroie", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AiDevelopment/donut-base-sroie with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AiDevelopment/donut-base-sroie

SGLang

How to use AiDevelopment/donut-base-sroie 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 "AiDevelopment/donut-base-sroie" \
    --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": "AiDevelopment/donut-base-sroie",
		"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 "AiDevelopment/donut-base-sroie" \
        --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": "AiDevelopment/donut-base-sroie",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AiDevelopment/donut-base-sroie with Docker Model Runner:
```
docker model run hf.co/AiDevelopment/donut-base-sroie
```

AiDevelopment commited on Jan 5, 2023

Commit

8f647a0

1 Parent(s): aa642b4

End of training

Browse files

Files changed (6) hide show

README.md +3 -4
preprocessor_config.json +4 -4
pytorch_model.bin +1 -1
runs/Jan05_13-49-31_489c69041b2d/events.out.tfevents.1672926575.489c69041b2d.41934.16 +2 -2
tokenizer.json +0 -0
tokenizer_config.json +1 -1

README.md CHANGED Viewed

@@ -1,5 +1,4 @@
 ---
-license: mit
 tags:
 - generated_from_trainer
 datasets:
@@ -14,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 # donut-base-sroie
-This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the imagefolder dataset.
 ## Model description
@@ -33,13 +32,13 @@ More information needed
 ### Training hyperparameters
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
 - train_batch_size: 2
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 50
 - mixed_precision_training: Native AMP
 ### Training results

 ---
 tags:
 - generated_from_trainer
 datasets:
 # donut-base-sroie
+This model was trained from scratch on the imagefolder dataset.
 ## Model description
 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 3.4707116138614145e-05
 - train_batch_size: 2
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
+- num_epochs: 30
 - mixed_precision_training: Native AMP
 ### Training results

preprocessor_config.json CHANGED Viewed

@@ -19,8 +19,8 @@
   "processor_class": "DonutProcessor",
   "resample": 2,
   "rescale_factor": 0.00392156862745098,
-  "size": [
-    720,
-    960
-  ]
 }

   "processor_class": "DonutProcessor",
   "resample": 2,
   "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 960,
+    "width": 720
+  }
 }

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fac51498772549460da7ddff3ecec15c3269a4e745135004af9058c5fad4a4f9
 size 809187097

 version https://git-lfs.github.com/spec/v1
+oid sha256:18b2f870cf9d1722f23208c689b1988a5d32a4e048c46f2c585ed519fa3a6dd8
 size 809187097

runs/Jan05_13-49-31_489c69041b2d/events.out.tfevents.1672926575.489c69041b2d.41934.16 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01b0f672d0718b66c12f444d10952247069ebd9184ddcd58a064de0450f7c56e
-size 8232

 version https://git-lfs.github.com/spec/v1
+oid sha256:a7e7ce85cb7e9c0b9f7d5237124efb41e911451f502002e6307b5dc5d2ac3391
+size 9841

tokenizer.json CHANGED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json CHANGED Viewed

@@ -11,7 +11,7 @@
     "single_word": false
   },
   "model_max_length": 1000000000000000019884624838656,
-  "name_or_path": "naver-clova-ix/donut-base",
   "pad_token": "<pad>",
   "processor_class": "DonutProcessor",
   "sep_token": "</s>",

     "single_word": false
   },
   "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "AiDevelopment/donut-base-sroie",
   "pad_token": "<pad>",
   "processor_class": "DonutProcessor",
   "sep_token": "</s>",