OpenGVLab

/

InternVL3_5-1B-HF

like 5

Follow

OpenGVLab 1.65k

This pull request aims to improve the discoverability and completeness of the InternVL3.5-1B model card. Based on the paper abstract and the model's described capabilities, I've added the following relevant tags to the metadata:

• multimodal: The model is explicitly described as an "open-source multimodal model."
• reasoning: The paper highlights "reasoning capability" as a significant advancement.
• agent: The model supports "GUI interaction and embodied agency," aligning with agentic tasks.
• llm: The model is an "open-source MLLM" (multimodal large language model).
• efficiency: The paper emphasizes "inference efficiency" as a key improvement.

All other existing information, including paper link, GitHub link, project page, and sample usage, is already well-documented and accurate.