---
language:
- en
- es
tags:
- vision-language
- image-to-text
- ocr
- safety-moderation
license: apache-2.0
metrics:
- bleu
- meteor
- rouge
---

# 👁️ Valdam Vision 2.5

**Valdam Vision 2.5** is a Multimodal Vision-Language Model (VLM) designed for scene description, spatial OCR, and Zero-Shot content moderation.

This release integrates visual patch projection from a pretrained Vision Transformer with a modular autoregressive Transformer Decoder.

---

## 🌟 Key Features

- **Autoregressive Text Generation:** Generates descriptions by applying cross-attention over visual patch embeddings.
- **Zero-Shot Moderation (Valdam Shield):** Content screening powered by CLIP ViT-L/14 semantic similarity matching.
- **Spatial Layout OCR:** Reconstructs read order and paragraphs from designs using spatial coordinates.
- **Inference Latency:** Optimized pipeline with an average response time of ~0.08s on standard hardware.

---

## 📦 Repository Structure

- **`model.safetensors`**: Model weights in safe-tensors format containing header metadata.
- **`architecture.py`**: Model architecture definition (ViT Encoder & Transformer Decoder).
- **`inference.py`**: Script to initialize and run local predictions.
- **`config.json`**: Hyperparameters and model configuration.
- **`vocab.json`**: Mapping of vocabulary tokens.

---

## 🚀 Quickstart

```python
from inference import ValdamVisionLocalPredictor

# Initialize the predictor
predictor = ValdamVisionLocalPredictor(
    safetensors_weights_path="model.safetensors",
    config_path="config.json",
    vocab_path="vocab.json",
    device="cuda"
)

# Run prediction on a preprocessed image tensor
result = predictor.predict(image_tensor)
print(f"Result: {result}")
```

### Website
[Visit us!](https://research.inserloft.com)