chenxwh / deepseek-vl2

Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

  • Public
  • 1.1K runs
  • GitHub
  • Weights
  • Paper
  • License
Run with an API
Playground API Examples README Versions
  1. Author
    @chenxwh
    Version
    cuda12.4-python3.11-torch2.4.0-X64
    Commit
    a8341f36dd3a87d29e5f7a46cfe74762c145fc09

    8ea88789

    Latest
  2. Author
    @chenxwh
    Version
    cuda12.4-python3.11-torch2.4.0-X64
    Commit
    a8341f36dd3a87d29e5f7a46cfe74762c145fc09

    035d8498

  3. Author
    @chenxwh
    Version
    cuda12.4-python3.11-torch2.4.0-X64
    Commit
    a8341f36dd3a87d29e5f7a46cfe74762c145fc09

    1066678a

  4. Author
    @chenxwh
    Version
    cuda12.4-python3.11-torch2.4.0-X64
    Commit
    a8341f36dd3a87d29e5f7a46cfe74762c145fc09

    7cc60798

  5. Author
    @chenxwh
    Version
    cuda12.4-python3.11-torch2.4.0-X64
    Commit
    a8341f36dd3a87d29e5f7a46cfe74762c145fc09

    d4133551