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

Libraries

How to use ProjectsbyGaurav/donut-base-gaurav-receipt with Transformers:

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

pipe = pipeline("image-text-to-text", model="ProjectsbyGaurav/donut-base-gaurav-receipt")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("ProjectsbyGaurav/donut-base-gaurav-receipt")
model = AutoModelForMultimodalLM.from_pretrained("ProjectsbyGaurav/donut-base-gaurav-receipt", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ProjectsbyGaurav/donut-base-gaurav-receipt with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ProjectsbyGaurav/donut-base-gaurav-receipt

SGLang

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

Docker Model Runner
How to use ProjectsbyGaurav/donut-base-gaurav-receipt with Docker Model Runner:
```
docker model run hf.co/ProjectsbyGaurav/donut-base-gaurav-receipt
```

ProjectsbyGaurav commited on Jan 8, 2024

Commit

aa0b9a9

1 Parent(s): ab60375

Training in progress, epoch 3

Browse files

Files changed (2) hide show

model.safetensors +1 -1
runs/Jan08_16-52-56_fa586e9f5d1c/events.out.tfevents.1704732797.fa586e9f5d1c.773.0 +2 -2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a728f5d5c2b8cb41c23a895901b4e2ef0553b368ed62aa6250ab468fb28dcf2d
 size 809193624

 version https://git-lfs.github.com/spec/v1
+oid sha256:fcae560e0eb3cf18714f3b5a7b44c98d2e971a2db7d7da7343050dd7fadc6cd2
 size 809193624

runs/Jan08_16-52-56_fa586e9f5d1c/events.out.tfevents.1704732797.fa586e9f5d1c.773.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b22cd23b691e671b46993c30379d6021c63bd99a1a05d55c99ca11dfa30ac7e7
-size 9108

 version https://git-lfs.github.com/spec/v1
+oid sha256:463acc893bcf8edded3894176a04a3ec6f488d68891c97775eeedbc68c2341af
+size 9619