https://github.com/lucataco/cog-llama-3-vision-alpha

Cog wrapper for qresearch/llama-3-vision-alpha
https://github.com/lucataco/cog-llama-3-vision-alpha

cog transformers

Last synced: 12 months ago
JSON representation

Cog wrapper for qresearch/llama-3-vision-alpha

• Host: GitHub
• URL: https://github.com/lucataco/cog-llama-3-vision-alpha
• Owner: lucataco
• Created: 2024-04-29T17:53:35.000Z (about 2 years ago)
• Default Branch: main
• Last Pushed: 2024-11-05T15:55:00.000Z (over 1 year ago)
• Last Synced: 2024-11-05T16:48:19.267Z (over 1 year ago)
• Topics: cog, transformers
• Language: Python
• Homepage: https://replicate.com/lucataco/llama-3-vision-alpha
• Size: 31.8 MB
• Stars: 10
• Watchers: 1
• Forks: 2
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# qresearch/llama-3-vision-alpha Cog Model

This is an implementation of [qresearch/llama-3-vision-alpha](https://huggingface.co/qresearch/llama-3-vision-alpha) as a [Cog](https://github.com/replicate/cog) model.

## Development

Follow the [model pushing guide](https://replicate.com/docs/guides/push-a-model) to push your own model to [Replicate](https://replicate.com).

## Basic Usage

To run a prediction:

    cog predict -i image=@frieren.jpg -i prompt="Describe the image"

![input](frieren.jpg)