mengwei0427

/

StreamVLN_Video_qwen_1_5_r2r_rxr_envdrop_scalevln

like 2

This PR adds a comprehensive model card for the StreamVLN model, significantly improving its discoverability and providing essential information for users.

Key additions include:

• Metadata:
  • pipeline_tag: robotics for relevant model searches.
  • library_name: transformers for proper integration and usage examples.
  • license: cc-by-nc-sa-4.0 for clarity on usage rights.
  • Additional tags: vision-language-model, video-language-model, navigation.
• Content:
  • A link to the paper: StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling.
  • Links to the project page (https://streamvln.github.io/) and the GitHub repository (https://github.com/OpenRobotLab/StreamVLN).
  • The paper's abstract, an "About" section, and details on available model checkpoints.
  • A Python usage example to demonstrate basic model interaction with the transformers library.
  • Citation and license information.