Veritas

Veritas is a multimodal model designed for image-to-text and text-to-text tasks. This repository contains the model weights and necessary configurations for inference.

Model Details

• Model Type: Multimodal / Image-Text-to-Text
• Framework: PyTorch
• Task: Image Captioning / Visual Question Answering (VQA)
• License: Apache 2.0

Usage

Using Hugging Face Transformers

You can load the model directly using the huggingface_hub or transformers library:

from huggingface_hub import snapshot_download

# Download the model
model_dir = snapshot_download(repo_id="freds0/Veritas")