PP-Chart2Table_safetensors

PP-Chart2Table

Introduction

PP-Chart2Table is a SOTA multimodal model developed by the PaddlePaddle team, specializing in chart parsing for both Chinese and English. Its high performance is driven by a novel "Shuffled Chart Data Retrieval" training task, which, combined with a refined token masking strategy, significantly improves its efficiency in converting charts to data tables. The model is further strengthened by an advanced data synthesis pipeline that uses high-quality seed data, RAG, and LLMs persona design to create a richer, more diverse training set. To address the challenge of large-scale unlabeled, out-of-distribution (OOD) data, the team implemented a two-stage distillation process, ensuring robust adaptability and generalization on real-world data. In-house benchmarks demonstrate that PP-Chart2Table not only outperforms models of a similar scale but also achieves performance on par with 7-billion parameter Vision Language Models (VLMs) in critical application scenarios.

<img src="https://cdn-uploads.huggingface.co/production/uploads/684acf07de103b2d44c85531/IsYzsgw5f8ehK4zn9IP1x.png"/>

Model Usage

import requests
from PIL import Image
from transformers import AutoModelForImageTextToText, AutoProcessor

model_path = "PaddlePaddle/PP-Chart2Table_safetensors"
model = AutoModelForImageTextToText.from_pretrained(
    model_path, 
    device_map="auto",
)
processor = AutoProcessor.from_pretrained(model_path)

# PPChart2TableProcessor uses hardcoded "Chart to table" instruction internally via chat template
conversation = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "url": "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/chart_parsing_02.png",
            },
        ],
    },
]

inputs = processor.apply_chat_template(
    conversation,
    tokenize=True, 
    add_generation_prompt=True, 
    truncation=True,
    return_dict=True,
    return_tensors="pt",
).to(model.device)

generated_ids = model.generate(**inputs, do_sample=False, max_new_tokens=256)
generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
result = processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)
print(result)