Instructions to use TomasFAV/Pix2StructCzechInvoiceV012 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TomasFAV/Pix2StructCzechInvoiceV012 with Transformers:

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

pipe = pipeline("image-text-to-text", model="TomasFAV/Pix2StructCzechInvoiceV012")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("TomasFAV/Pix2StructCzechInvoiceV012")
model = AutoModelForImageTextToText.from_pretrained("TomasFAV/Pix2StructCzechInvoiceV012")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TomasFAV/Pix2StructCzechInvoiceV012 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TomasFAV/Pix2StructCzechInvoiceV012"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TomasFAV/Pix2StructCzechInvoiceV012",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TomasFAV/Pix2StructCzechInvoiceV012

SGLang

How to use TomasFAV/Pix2StructCzechInvoiceV012 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/Pix2StructCzechInvoiceV012" \
    --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/Pix2StructCzechInvoiceV012",
		"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/Pix2StructCzechInvoiceV012" \
        --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/Pix2StructCzechInvoiceV012",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TomasFAV/Pix2StructCzechInvoiceV012 with Docker Model Runner:
```
docker model run hf.co/TomasFAV/Pix2StructCzechInvoiceV012
```

Pix2StructCzechInvoiceV012 / generation_config.json

TomasFAV

Training in progress, epoch 1

8cbff93 verified 2 months ago

raw

history blame contribute delete

979 Bytes

	{
	"_from_model_config": false,
	"assistant_confidence_threshold": 0.4,
	"assistant_lookbehind": 10,
	"decoder_start_token_id": 0,
	"diversity_penalty": 0.0,
	"do_sample": false,
	"early_stopping": false,
	"encoder_no_repeat_ngram_size": 0,
	"encoder_repetition_penalty": 1.0,
	"eos_token_id": 1,
	"epsilon_cutoff": 0.0,
	"eta_cutoff": 0.0,
	"is_vqa": true,
	"length_penalty": 1.0,
	"max_length": 20,
	"min_length": 0,
	"no_repeat_ngram_size": 0,
	"num_assistant_tokens": 20,
	"num_assistant_tokens_schedule": "constant",
	"num_beam_groups": 1,
	"num_beams": 1,
	"num_return_sequences": 1,
	"output_attentions": false,
	"output_hidden_states": false,
	"output_scores": false,
	"pad_token_id": 0,
	"remove_invalid_values": false,
	"repetition_penalty": 1.0,
	"return_dict_in_generate": false,
	"target_lookbehind": 10,
	"temperature": 1.0,
	"top_k": 50,
	"top_p": 1.0,
	"transformers_version": "5.0.0",
	"typical_p": 1.0,
	"use_cache": false
	}