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

Libraries

How to use nielsr/donut-base-finetuned-rvlcdip with Transformers:

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

pipe = pipeline("image-text-to-text", model="nielsr/donut-base-finetuned-rvlcdip")

# Load model directly
from transformers import AutoTokenizer, AutoModelForImageTextToText

tokenizer = AutoTokenizer.from_pretrained("nielsr/donut-base-finetuned-rvlcdip")
model = AutoModelForImageTextToText.from_pretrained("nielsr/donut-base-finetuned-rvlcdip")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use nielsr/donut-base-finetuned-rvlcdip with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/nielsr/donut-base-finetuned-rvlcdip

SGLang

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

Docker Model Runner
How to use nielsr/donut-base-finetuned-rvlcdip with Docker Model Runner:
```
docker model run hf.co/nielsr/donut-base-finetuned-rvlcdip
```

nielsr HF Staff commited on Jul 25, 2022

Commit

f933c7f

1 Parent(s): d25460e

add model

Browse files

Files changed (6) hide show

added_tokens.json +24 -0
preprocessor_config.json +22 -0
sentencepiece.bpe.model +3 -0
special_tokens_map.json +38 -0
tokenizer.json +0 -0
tokenizer_config.json +22 -0

added_tokens.json ADDED Viewed

	@@ -0,0 +1,24 @@

+{
+  "</s_class>": 57523,
+  "<advertisement/>": 57524,
+  "<budget/>": 57525,
+  "<email/>": 57526,
+  "<file_folder/>": 57527,
+  "<form/>": 57528,
+  "<handwritten/>": 57529,
+  "<invoice/>": 57530,
+  "<letter/>": 57531,
+  "<memo/>": 57532,
+  "<news_article/>": 57533,
+  "<presentation/>": 57534,
+  "<questionnaire/>": 57535,
+  "<resume/>": 57536,
+  "<s_class>": 57537,
+  "<s_iitcdip>": 57538,
+  "<s_rvlcdip>": 57539,
+  "<s_synthdog>": 57540,
+  "<scientific_publication/>": 57541,
+  "<scientific_report/>": 57542,
+  "<sep/>": 57522,
+  "<specification/>": 57543
+}

preprocessor_config.json ADDED Viewed

	@@ -0,0 +1,22 @@

+{
+  "do_normalize": true,
+  "do_pad": true,
+  "do_resize_and_thumbnail": true,
+  "feature_extractor_type": "DonutFeatureExtractor",
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "DonutProcessor",
+  "resample": 2,
+  "size": [
+    1920,
+    2560
+  ]
+}

sentencepiece.bpe.model ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:cb9e3dce4c326195d08fc3dd0f7e2eee1da8595c847bf4c1a9c78b7a82d47e2d
+size 1296245

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,38 @@

+{
+  "additional_special_tokens": [
+    "</s_class>",
+    "<advertisement/>",
+    "<budget/>",
+    "<email/>",
+    "<file_folder/>",
+    "<form/>",
+    "<handwritten/>",
+    "<invoice/>",
+    "<letter/>",
+    "<memo/>",
+    "<news_article/>",
+    "<presentation/>",
+    "<questionnaire/>",
+    "<resume/>",
+    "<s_class>",
+    "<s_iitcdip>",
+    "<s_rvlcdip>",
+    "<s_synthdog>",
+    "<scientific_publication/>",
+    "<scientific_report/>",
+    "<specification/>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json ADDED Viewed

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

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,22 @@

+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "from_slow": true,
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "name_or_path": "naver-clova-ix/donut-base-finetuned-rvlcdip",
+  "pad_token": "<pad>",
+  "processor_class": "DonutProcessor",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}