Nalandadata

DrishtiTable-Qwen2.5-VL-7B

README

License: apache-2.0

Results

Table with columns: Model, Method, TEDS, S-TEDS
Model	Method	TEDS	S-TEDS
Qwen2.5-VL-7B	Zero-shot	58.8%	74.0%
o4-mini (OpenAI)	Zero-shot	61.4%	70.0%
GPT-4.1 (OpenAI)	Zero-shot	68.0%	80.8%
GPT-4o (OpenAI)	Zero-shot	71.1%	84.3%
DrishtiTable-Qwen2.5-VL-7B (ours)	SFT	83.2%	89.7%

Breakdown by Table Type

Table with columns: Table Type, GPT-4o, Ours, Improvement
Table Type	GPT-4o	Ours	Improvement
Statistical	77.7%	82.8%	+5.1
Financial	60.3%	82.0%	+21.7
Lookup	71.7%	85.7%	+14.0
Comparison	72.4%	95.9%	+23.5

Usage

With Unsloth (Recommended)

python
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
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

Table with columns: Parameter, Value
Parameter	Value
Base model	Qwen2.5-VL-7B-Instruct
Method	QLoRA (4-bit) via Unsloth
LoRA rank	32
LoRA alpha	32
Target modules	all-linear (incl. vision layers)
Training data	1,141 table images from DrishtiTable
Epochs	3
Learning rate	2e-4 (cosine schedule)
Batch size

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

Table with columns: Resource, Link
Resource	Link
Live Demo	DrishtiTable Space
Dataset (sample)	Nalandadata/DrishtiTable
Base Model	Qwen/Qwen2.5-VL-7B-Instruct

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
@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

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Container

Run this model inference with full control and performance in your environment.

Learn more

Model Details

Model Provider

Nalandadata

Model Tree

Base

Qwen/Qwen2.5-VL-7B-Instruct

Adapter

this model

Input Modalities

TextImage

Output Modalities

Text

Supported Functionality

Dedicated EndpointsContainer

Explore FriendliAI today

Get started Talk to an engineer