GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
Rem520
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
Rem520
Model Tree
zhibinlan/UME-R1-7B
Input Modalities
Output Modalities
Supported Functionality
zhibinlan/UME-R1-7B (Qwen2-VL-7B, Qwen2VLForConditionalGeneration)The weights load as a standard Qwen2-VL checkpoint:
python
from transformers import AutoProcessor, Qwen2VLForConditionalGenerationmodel = Qwen2VLForConditionalGeneration.from_pretrained("Rem520/PLUME-7B", torch_dtype="auto", device_map="auto")processor = AutoProcessor.from_pretrained("Rem520/PLUME-7B")
To use the full PLUME embedding pipeline (latent rollout + semantic-anchor-guided transition adapter), follow the official code: https://github.com/haoxiangzhao12138/PLUME
bibtex
@article{he2026plume,title = {PLUME: Latent Reasoning Based Universal Multimodal Embedding},author = {He, Chenwei and Hao, Xiangzhao and Yang, Tianyu and Ma, Yuxiang andJia, Yuheng and Wu, Lingxiang and Zhao, Chaoyang and Guo, Haiyun and Wang, Jinqiao},journal = {arXiv preprint arXiv:2604.02073},year = {2026}}