Patram-7B - Indian Document Vision-Language Model

Patram-7B - Indian Document Vision-Language Model

Open-source 7B parameter vision-language model specifically trained for Indian document understanding, from government forms to handwritten pages. Handles the varied structure of scanned and photographed Indian documents including Devanagari text. Achieves strong scores on DocVQA (0.855), VisualMRC (0.851), and the custom Patram-Bench. Can be fine-tuned for specific Marathi document types (7/12 extracts, certificates, forms). Represents the current state-of-the-art in open-source Indian document AI.

Fine-tune Patram-7B on Maharashtra government documents (7/12 extracts, certificates) for automated field extraction.
HomepageHuggingFace

Quick Start

from transformers import AutoModelForVision2Seq, AutoProcessor
from PIL import Image

model = AutoModelForVision2Seq.from_pretrained("bharatgenai/patram-7b-instruct")
processor = AutoProcessor.from_pretrained("bharatgenai/patram-7b-instruct")

image = Image.open("marathi_document.jpg")
prompt = "Extract all field values from this Marathi document"
# inputs = processor(images=image, text=prompt, return_tensors="pt")
print("Patram-7B: Indian document VLM for Marathi form understanding")
Modality
Model (Vision-Language Model for document understanding)
Size
7B parameters
License
Format
Model weights (Safetensors)
Language
mr, hi, en, bn, ta, te
Update Frequency
static
Organization
BharatGenAI

Schema

FieldTypeDescription
input_imageimageDocument image (scanned or photographed)
querystringQuestion or extraction instruction about the document
responsestringExtracted text, field values, or answer

Build With This

Create a Maharashtra e-governance document processor using Patram-7B to automatically extract and validate form fields
Develop a multilingual Indian document QA system handling mixed Marathi-English government documents
Build a document digitization pipeline combining Patram-7B with post-OCR correction for end-to-end Marathi document understanding

AI Use Cases

Marathi government document OCR and understandingIndian form field extractionDocument visual question answering in Indian languagesZero-shot document classification for Indian documents
Last verified: 2026-03-12