GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Nalandadata
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Nalandadata
Model Tree
Qwen/Qwen2.5-VL-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
| 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% |
| 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 |
python
from unsloth import FastVisionModelfrom qwen_vl_utils import process_vision_infofrom PIL import Image # Load modelmodel, tokenizer = FastVisionModel.from_pretrained( "Nalandadata/DrishtiTable-Qwen2.5-VL-7B", max_seq_length=4096, load_in_4bit=True,)FastVisionModel.for_inference(model) # Prepare inputimage = 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."}, ]},] # Generatetext = 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)python
from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessorfrom peft import PeftModelimport 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")| 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 | 1 (gradient accumulation 8) |
| Max sequence length | 4,096 |
| Optimizer | AdamW 8-bit |
| Hardware | 1x NVIDIA A100-80GB |
| Training time | ~35 minutes |
| Training cost | ~$5 (Modal cloud) |
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.
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.
| Resource | Link |
|---|---|
| Live Demo | DrishtiTable Space |
| Dataset (sample) | Nalandadata/DrishtiTable |
| Base Model | Qwen/Qwen2.5-VL-7B-Instruct |
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}}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:
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
from unsloth import FastVisionModelfrom qwen_vl_utils import process_vision_infofrom PIL import Image # Load modelmodel, tokenizer = FastVisionModel.from_pretrained( "Nalandadata/DrishtiTable-Qwen2.5-VL-7B", max_seq_length=4096, load_in_4bit=True,)FastVisionModel.for_inference(model) # Prepare inputimage = 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."}, ]},] # Generatetext = 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)from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessorfrom peft import PeftModelimport 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")@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}}