Instructions to use TomasFAV/Pix2StructCzechInvoiceV01 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TomasFAV/Pix2StructCzechInvoiceV01 with Transformers:

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

pipe = pipeline("image-text-to-text", model="TomasFAV/Pix2StructCzechInvoiceV01")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("TomasFAV/Pix2StructCzechInvoiceV01")
model = AutoModelForImageTextToText.from_pretrained("TomasFAV/Pix2StructCzechInvoiceV01")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TomasFAV/Pix2StructCzechInvoiceV01 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TomasFAV/Pix2StructCzechInvoiceV01"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TomasFAV/Pix2StructCzechInvoiceV01",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TomasFAV/Pix2StructCzechInvoiceV01

SGLang

How to use TomasFAV/Pix2StructCzechInvoiceV01 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/Pix2StructCzechInvoiceV01" \
    --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/Pix2StructCzechInvoiceV01",
		"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/Pix2StructCzechInvoiceV01" \
        --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/Pix2StructCzechInvoiceV01",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TomasFAV/Pix2StructCzechInvoiceV01 with Docker Model Runner:
```
docker model run hf.co/TomasFAV/Pix2StructCzechInvoiceV01
```

Pix2StructCzechInvoiceV01 / config.json

TomasFAV

Training in progress, epoch 1

1dc42df verified 2 months ago

raw

history blame contribute delete

2.61 kB

	{
	"architectures": [
	"Pix2StructForConditionalGeneration"
	],
	"decoder_start_token_id": 0,
	"dtype": "float32",
	"eos_token_id": 1,
	"initializer_factor": 1.0,
	"initializer_range": 0.02,
	"is_encoder_decoder": true,
	"is_vqa": true,
	"model_type": "pix2struct",
	"pad_token_id": 0,
	"text_config": {
	"add_cross_attention": false,
	"bos_token_id": null,
	"cross_attention_hidden_size": null,
	"d_ff": 2048,
	"d_kv": 64,
	"decoder_start_token_id": 0,
	"dense_act_fn": "gelu_new",
	"dropout_rate": 0.1,
	"dtype": "float32",
	"encoder_hidden_size": 768,
	"eos_token_id": 1,
	"finetuning_task": null,
	"hidden_size": 768,
	"initializer_factor": 1.0,
	"initializer_range": 0.02,
	"is_decoder": true,
	"is_encoder_decoder": true,
	"layer_norm_epsilon": 1e-06,
	"model_type": "pix2struct_text_model",
	"num_heads": 12,
	"num_layers": 12,
	"pad_token_id": 0,
	"prefix": null,
	"pruned_heads": {},
	"relative_attention_max_distance": 128,
	"relative_attention_num_buckets": 32,
	"sep_token_id": null,
	"task_specific_params": null,
	"tf_legacy_loss": false,
	"tie_encoder_decoder": false,
	"tie_word_embeddings": false,
	"tokenizer_class": null,
	"torchscript": false,
	"use_bfloat16": false,
	"use_cache": false,
	"vocab_size": 50432
	},
	"tie_word_embeddings": false,
	"transformers_version": "5.0.0",
	"use_cache": false,
	"vision_config": {
	"add_cross_attention": false,
	"attention_dropout": 0.0,
	"bos_token_id": null,
	"cross_attention_hidden_size": null,
	"d_ff": 2048,
	"d_kv": 64,
	"decoder_start_token_id": null,
	"dense_act_fn": "gelu_new",
	"dropout_rate": 0.0,
	"dtype": "float32",
	"eos_token_id": null,
	"finetuning_task": null,
	"hidden_size": 768,
	"initializer_factor": 1.0,
	"initializer_range": 0.02,
	"is_decoder": false,
	"layer_norm_bias": false,
	"layer_norm_eps": 1e-06,
	"model_type": "pix2struct_vision_model",
	"num_attention_heads": 12,
	"num_channels": 3,
	"num_hidden_layers": 12,
	"pad_token_id": null,
	"patch_embed_hidden_size": 768,
	"patch_size": 16,
	"prefix": null,
	"projection_dim": 768,
	"pruned_heads": {},
	"relative_attention_max_distance": 128,
	"relative_attention_num_buckets": 32,
	"sep_token_id": null,
	"seq_len": 4096,
	"task_specific_params": null,
	"tf_legacy_loss": false,
	"tie_encoder_decoder": false,
	"tie_word_embeddings": true,
	"tokenizer_class": null,
	"torchscript": false,
	"use_bfloat16": false
	}
	}