https://github.com/charles-zhng/seeing-eye-dog

learning to use mlx by doing vlm inference with quantized models

https://github.com/charles-zhng/seeing-eye-dog

Science Score: 13.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (2.9%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

learning to use mlx by doing vlm inference with quantized models

Basic Info
  • Host: GitHub
  • Owner: charles-zhng
  • Language: Jupyter Notebook
  • Default Branch: main
  • Size: 2.44 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created almost 2 years ago · Last pushed almost 2 years ago
Metadata Files
Readme

README.md

seeing-eye-dog

except it talks to you in english and it's just your phone

learning to use mlx by

  1. doing vlm inference with quantized models.
  2. deploy on device for (hopefully) realtime inference
  3. make it better idk

todos

[x] baby's first local inference [ ] connect to laptop webcam to get images (start off sampling every 5 secs or so) [ ] text to speech (in future use fusion model to directly go from image/prompt to speech) [ ] make it faster

Owner

  • Name: Charles Zhang
  • Login: charles-zhng
  • Kind: user

GitHub Events

Total
  • Watch event: 1
Last Year
  • Watch event: 1