Instructions to use arif11/pix2struct-base-table2html with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use arif11/pix2struct-base-table2html with Transformers:

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

pipe = pipeline("image-text-to-text", model="arif11/pix2struct-base-table2html")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("arif11/pix2struct-base-table2html")
model = AutoModelForImageTextToText.from_pretrained("arif11/pix2struct-base-table2html")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use arif11/pix2struct-base-table2html with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "arif11/pix2struct-base-table2html"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "arif11/pix2struct-base-table2html",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/arif11/pix2struct-base-table2html

SGLang

How to use arif11/pix2struct-base-table2html 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 "arif11/pix2struct-base-table2html" \
    --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": "arif11/pix2struct-base-table2html",
		"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 "arif11/pix2struct-base-table2html" \
        --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": "arif11/pix2struct-base-table2html",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use arif11/pix2struct-base-table2html with Docker Model Runner:
```
docker model run hf.co/arif11/pix2struct-base-table2html
```

pix2struct-base-table2html / config.json

arif11

Upload Pix2StructForConditionalGeneration

9b59d3c verified about 1 year ago

raw

history blame contribute delete

995 Bytes

	{
	"_name_or_path": "KennethTM/pix2struct-base-table2html",
	"architectures": [
	"Pix2StructForConditionalGeneration"
	],
	"decoder_start_token_id": 0,
	"eos_token_id": 1,
	"initializer_factor": 1.0,
	"initializer_range": 0.02,
	"is_encoder_decoder": true,
	"is_vqa": false,
	"model_type": "pix2struct",
	"pad_token_id": 0,
	"text_config": {
	"_attn_implementation_autoset": true,
	"dropout_rate": 0.2,
	"encoder_hidden_size": 768,
	"initializer_range": 0.02,
	"is_encoder_decoder": true,
	"model_type": "pix2struct_text_model"
	},
	"tie_word_embeddings": false,
	"torch_dtype": "float32",
	"transformers_version": "4.48.3",
	"vision_config": {
	"_attn_implementation_autoset": true,
	"attention_dropout": 0.2,
	"dropout_rate": 0.2,
	"hidden_dropout_prob": 0.2,
	"initializer_range": 0.02,
	"layer_norm_bias": false,
	"model_type": "pix2struct_vision_model",
	"num_channels": 3,
	"patch_size": 16,
	"projection_dim": 768
	}
	}