Instructions to use TomasFAV/Pix2StructCzechInvoiceV0R with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TomasFAV/Pix2StructCzechInvoiceV0R with Transformers:

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

pipe = pipeline("image-text-to-text", model="TomasFAV/Pix2StructCzechInvoiceV0R")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("TomasFAV/Pix2StructCzechInvoiceV0R")
model = AutoModelForImageTextToText.from_pretrained("TomasFAV/Pix2StructCzechInvoiceV0R")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TomasFAV/Pix2StructCzechInvoiceV0R with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TomasFAV/Pix2StructCzechInvoiceV0R"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TomasFAV/Pix2StructCzechInvoiceV0R",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TomasFAV/Pix2StructCzechInvoiceV0R

SGLang

How to use TomasFAV/Pix2StructCzechInvoiceV0R 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 "TomasFAV/Pix2StructCzechInvoiceV0R" \
    --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": "TomasFAV/Pix2StructCzechInvoiceV0R",
		"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 "TomasFAV/Pix2StructCzechInvoiceV0R" \
        --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": "TomasFAV/Pix2StructCzechInvoiceV0R",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TomasFAV/Pix2StructCzechInvoiceV0R with Docker Model Runner:
```
docker model run hf.co/TomasFAV/Pix2StructCzechInvoiceV0R
```

TomasFAV commited on Mar 27

Commit

b5ebd30

1 Parent(s): 8b1c68d

Training in progress, epoch 1

Browse files

Files changed (3) hide show

model.safetensors +1 -1
runs/Mar27_18-13-27_acccecfffd25/events.out.tfevents.1774635207.acccecfffd25.3363.0 +3 -0
training_args.bin +1 -1

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2de36a82e6bf49c975f0fffb63ab61bbd36ea20a7124418c1c7e6a08ae161d5
 size 1130333048

 version https://git-lfs.github.com/spec/v1
+oid sha256:83ebf38eb10c5ca6bfc03519063f2cadd5d0858dc5832cf06b72979d2cc9b616
 size 1130333048

runs/Mar27_18-13-27_acccecfffd25/events.out.tfevents.1774635207.acccecfffd25.3363.0 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:66d342858aea0415711802fdd436063f313c7a8d65618e487a7d25539028142a
+size 10088

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56eae8dcd443552f14850f7cd98c1a264a724cceaaa5c9febfd097023d41119f
 size 5393

 version https://git-lfs.github.com/spec/v1
+oid sha256:dbcc4ecd186f556cac9f95cd640e568ad6ea22c343b153197f382e039d83e731
 size 5393