Video-Text-to-Text
Safetensors
qwen2_5_vl
robotic-manipulation
reinforcement-learning
chain-of-thought

Commit History

  1. Card: import prompt constants from primo_prompts / frame helper from primo_video_utils

    Verified signature
    4d452de

  1. Move DeepSpeed resume state to the training-state branch

    Verified signature
    0ef2acf
  2. Add usage example, interleaved input spec, and download guidance

    Verified signature
    cdb4797

  1. Upload folder using huggingface_hub

    Verified signature
    eb1187c

  1. Update README.md

    Verified signature
    3357b50

  1. Update README.md

    Verified signature
    0dad362
  2. Update README.md

    Verified signature
    a69b2df

  1. Update model card with description and paper link (#1)⁠

    LeonOverload +1: nielsr
    91d8892

  1. Update README.md

    Verified signature
    f084cf7
  2. Update README.md

    Verified signature
    bfbb6e4

  1. initial commit

    Verified signature
    e1aca94