Instructions to use HamAndCheese82/math-ocr-donut-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HamAndCheese82/math-ocr-donut-v2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="HamAndCheese82/math-ocr-donut-v2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("HamAndCheese82/math-ocr-donut-v2")
model = AutoModelForMultimodalLM.from_pretrained("HamAndCheese82/math-ocr-donut-v2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HamAndCheese82/math-ocr-donut-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HamAndCheese82/math-ocr-donut-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HamAndCheese82/math-ocr-donut-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/HamAndCheese82/math-ocr-donut-v2

SGLang

How to use HamAndCheese82/math-ocr-donut-v2 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 "HamAndCheese82/math-ocr-donut-v2" \
    --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": "HamAndCheese82/math-ocr-donut-v2",
		"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 "HamAndCheese82/math-ocr-donut-v2" \
        --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": "HamAndCheese82/math-ocr-donut-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use HamAndCheese82/math-ocr-donut-v2 with Docker Model Runner:
```
docker model run hf.co/HamAndCheese82/math-ocr-donut-v2
```

HamAndCheese82 commited on Apr 24, 2024

Commit

4fb686e

verified ·

1 Parent(s): 2b6c548

On validation process, epoch 3, global step 145987

Browse files

Files changed (2) hide show

tokenizer.json +0 -0
tokenizer_config.json +7 -0

tokenizer.json CHANGED Viewed

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

tokenizer_config.json CHANGED Viewed

@@ -130,11 +130,18 @@
   "cls_token": "<s>",
   "eos_token": "</s>",
   "mask_token": "<mask>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "processor_class": "DonutProcessor",
   "sep_token": "</s>",
   "sp_model_kwargs": {},
   "tokenizer_class": "XLMRobertaTokenizer",
   "unk_token": "<unk>"
 }

   "cls_token": "<s>",
   "eos_token": "</s>",
   "mask_token": "<mask>",
+  "max_length": 512,
   "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "processor_class": "DonutProcessor",
   "sep_token": "</s>",
   "sp_model_kwargs": {},
+  "stride": 0,
   "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }