metadata

base_model:
  - meta-llama/Llama-3.1-8B-Instruct
pipeline_tag: text-generation
library_name: transformers

Llama-3.2-1B-Vision

A vision-enhanced version of the Llama-3.1-8B language model, capable of understanding and describing images while maintaining the base model's language capabilities.

Model Details

Base Model: Llama-3.1-8B
Model Type: Vision-Language Model
Last Updated: December ?, 2024
Model Architecture: Llama architecture with SigLIP vision encoder