DrishtiTable-Qwen2.5-VL-7B

Results

Breakdown by Table Type

Usage

With Unsloth (Recommended)

python
Copy code
from unsloth import FastVisionModel
from qwen_vl_utils import process_vision_info
from PIL import Image

# Load model
model, tokenizer = FastVisionModel.from_pretrained(
    "Nalandadata/DrishtiTable-Qwen2.5-VL-7B",
    max_seq_length=4096,
    load_in_4bit=True,
)
FastVisionModel.for_inference(model)

# Prepare input
image = Image.open("table.png").convert("RGB")
messages = [
    {"role": "system", "content": "You are a table structure recognition expert. Given an image of a table, output the HTML representation of the table structure and content. Use <table>, <thead>, <tbody>, <tr>, <th>, <td> tags. Use colspan and rowspan attributes for merged cells. Output ONLY the HTML table, nothing else."},
    {"role": "user", "content": [
        {"type": "image", "image": image},
        {"type": "text", "text": "Convert this table image to HTML. Output only the HTML table structure with cell content."},
    ]},
]

# Generate
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
image_inputs, video_inputs = process_vision_info(messages)
inputs = tokenizer(text=[text], images=image_inputs, videos=video_inputs,
                   padding=True, return_tensors="pt").to(model.device)

output = model.generate(**inputs, max_new_tokens=4096, do_sample=False)
generated = [o[len(i):] for i, o in zip(inputs.input_ids, output)]
html = tokenizer.batch_decode(generated, skip_special_tokens=True)[0].strip()
print(html)

With Transformers + PEFT

python
Copy code
from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor
from peft import PeftModel
import torch

base_model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
    "Qwen/Qwen2.5-VL-7B-Instruct",
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
model = PeftModel.from_pretrained(base_model, "Nalandadata/DrishtiTable-Qwen2.5-VL-7B")
processor = AutoProcessor.from_pretrained("Nalandadata/DrishtiTable-Qwen2.5-VL-7B")

Training Details

Dataset

Trained on DrishtiTable -- 1,421 table images from 9 Indian academic textbooks (S. Chand Publications) spanning Financial Accounting, Business Statistics, Quantitative Techniques, Operation Research, Ethics, and Engineering Steam Tables.

Evaluation

Evaluated using TEDS (Tree Edit Distance Similarity), the standard metric for table structure recognition. TEDS measures structural and content similarity between predicted and ground-truth HTML table trees on a 0-100% scale.

Links

Limitations

• Trained on tables from a single publisher (S. Chand Publications); performance on other publishers/styles is untested
• Optimized for Indian academic textbook tables; may not generalize to web tables, handwritten tables, or camera-captured tables
• HTML output may contain OCR errors in cell text content (S-TEDS 89.7% > TEDS 83.2%)

Citation

bibtex
Copy code
@article{drishtitable2026,
  title={Domain-Specific Fine-Tuning for Table Structure Recognition: A 7B Open Model Outperforms GPT-4o with 1,141 Training Samples},
  author={Nalanda Data},
  year={2026}
}

Commercial Use & Support

This model is released under Apache 2.0. The training data (DrishtiTable) is a public sample of a larger internal corpus of 1,421 expert-annotated tables from Indian academic textbooks.

Available on request:

• Custom fine-tuned TSR models for your document layouts
• Production deployment support (vLLM, quantization, serving)
• Access to the full training corpus under custom commercial license terms
• Partnerships for document-understanding evaluation and integration

Contact

For commercial licensing, full dataset access, custom data work, or partnerships:
📧 info@nalandadata.ai

For technical questions, integration help, or fine-tuning support:
📧 tech@nalandadata.ai

🌐 nalandadata.ai