Instructions to use eduvedras/ChartDataModel_Pix2Struct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use eduvedras/ChartDataModel_Pix2Struct with Transformers:

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

pipe = pipeline("image-text-to-text", model="eduvedras/ChartDataModel_Pix2Struct")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("eduvedras/ChartDataModel_Pix2Struct")
model = AutoModelForMultimodalLM.from_pretrained("eduvedras/ChartDataModel_Pix2Struct")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use eduvedras/ChartDataModel_Pix2Struct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "eduvedras/ChartDataModel_Pix2Struct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "eduvedras/ChartDataModel_Pix2Struct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/eduvedras/ChartDataModel_Pix2Struct

SGLang

How to use eduvedras/ChartDataModel_Pix2Struct 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 "eduvedras/ChartDataModel_Pix2Struct" \
    --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": "eduvedras/ChartDataModel_Pix2Struct",
		"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 "eduvedras/ChartDataModel_Pix2Struct" \
        --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": "eduvedras/ChartDataModel_Pix2Struct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use eduvedras/ChartDataModel_Pix2Struct with Docker Model Runner:
```
docker model run hf.co/eduvedras/ChartDataModel_Pix2Struct
```

ChartDataModel_Pix2Struct / config.json

eduvedras

Upload Pix2StructForConditionalGeneration

811be52 verified about 2 years ago

Raw

History Blame Contribute Delete

1.01 kB

	{
	"_name_or_path": "google/pix2struct-textcaps-base",
	"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": {
	"dropout_rate": 0.05,
	"encoder_hidden_size": 768,
	"feed_forward_proj": "gated-gelu",
	"initializer_range": 0.02,
	"is_gated_act": true,
	"model_type": "pix2struct_text_model"
	},
	"tie_word_embeddings": false,
	"torch_dtype": "float32",
	"transformers_version": "4.41.2",
	"vision_config": {
	"attention_dropout": 0.05,
	"dropout_rate": 0.06,
	"hidden_dropout_prob": 0.05,
	"image_size": 384,
	"initializer_range": 0.02,
	"layer_norm_bias": false,
	"mlp_bias": false,
	"model_type": "pix2struct_vision_model",
	"num_channels": 3,
	"patch_size": 16,
	"projection_dim": 768,
	"qkv_bias": false
	}
	}