yorickvp / llava-13b

Visual instruction tuning towards large language and vision models with GPT-4 level capabilities

  • Public
  • 17.7M runs
  • GitHub
  • Paper
  • License
  1. 80537f9e

    Latest
  2. Author
    @jd7h

    This version has been automatically upgraded to a newer version.

  3. This version has been automatically upgraded to a newer version.