GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
wwwbbb2003
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
wwwbbb2003
Model Tree
Qwen/Qwen2.5-VL-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
| Checkpoint | Base Model | Architecture | Parameters | Description | Link |
|---|---|---|---|---|---|
RoboInter-VLM (this repo) | Qwen2.5-VL-7B-Instruct | Qwen2.5-VL | ~7B | Flagship model, recommended for best performance | https://huggingface.co/InternRobotics/RoboInter-VLM |
RoboInter-VLM_qwenvl25_3b | Qwen2.5-VL-3B-Instruct | Qwen2.5-VL | ~3B | Lightweight model, suitable for efficient deployment | https://huggingface.co/InternRobotics/RoboInter-VLM_qwenvl25_3b |
RoboInter-VLM_llavaov_7B | LLaVA-OneVision-Qwen2-7B | LLaVA-OneVision | ~7B | LLaVA-OneVision backbone with SigLIP vision encoder | https://huggingface.co/InternRobotics/RoboInter-VLM_llavaov_7B |
All checkpoints are stored in safetensors format with bfloat16 precision.
These models are jointly trained on general VQA and three categories of our curated VQA tasks:
python
from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessormodel_path = "InternRobotics/RoboInter-VLM"model = Qwen2_5_VLForConditionalGeneration.from_pretrained(model_path, torch_dtype="auto", device_map="auto")processor = AutoProcessor.from_pretrained(model_path)
For detailed usage and inference examples, please refer to the RoboInterVLM-QwenVL codebase.
For loading and inference with the LLaVA-OneVision checkpoint, please refer to the RoboInterVLM-LLaVAOV codebase, as it requires custom model classes.
For full training and evaluation pipelines, please refer to:
If you find RoboInter useful in your research, please consider citing:
bibtex
@article{li2026robointer,title={RoboInter: A Holistic Intermediate Representation Suite Towards Robotic Manipulation},author={Li, Hao and Wang, Ziqin and Ding, Zi-han and Yang, Shuai and Chen, Yilun and Tian, Yang and Hu, Xiaolin and Wang, Tai and Lin, Dahua and Zhao, Feng and Liu, Si and Pang, Jiangmiao},journal={arXiv preprint arXiv:2602.09973},year={2025}}
Please refer to the original licenses of RoboInter, Qwen2.5-VL, and LLaVA-OneVision.