license: apache-2.0
base_model:
- Qwen/Qwen2.5-VL-3B-Instruct
- Qwen/Qwen2.5-VL-7B-Instruct
- lmms-lab/llava-onevision-qwen2-7b-ov
tags:
- robotics
- vision-language-action-model
- vision-language-model
library_name: transformers

# Collection Metadata (Referencing InternRobotics/VLN-PE style)
repo: InternRobotics/RoboInter-VLM
type: "checkpoint-collection"
description: "Collection of RoboInterVLM checkpoints and configs fine-tuned on RoboInter-VQA."
checkpoints:
  - name: RoboInterVLM_qwenvl25_3b
    path: RoboInterVLM_qwenvl25_3b/
    notes: "Lightweight Qwen2.5-VL model"
  - name: RoboInterVLM_qwenvl25_7b
    path: RoboInterVLM_qwenvl25_7b/
    notes: "Stronger performance Qwen2.5-VL backbone"
  - name: RoboInterVLM_llava_one_vision_7B
    path: RoboInterVLM_llava_one_vision_7B/
    notes: "LLaVA-OneVision (SigLIP + Qwen2) backbone"