OpenBMB releases Trident-Qwen3VL-2B multimodal embedding model on Hugging Face
Overview
OpenBMB releases Trident-Qwen3VL-2B, an open multimodal embedding model that maps text, images, and fused text-image inputs into one shared space for mixed-modality retrieval.
The model is fine-tuned from Qwen3-VL-2B-Instruct on the Trident-Train dataset, with the LoRA adapter already merged into the weights.
The Trident-specific weights are released under the MIT License. The base model's Apache-2.0 terms still apply, according to the release report.
Written by AI from the articles below · updated Oct 12, 9:59 AM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
- OpenBMB (MiniCPM) · new models on Hugging FaceOfficialTrident-Qwen3VL-2B: an open multimodal embedding model for mixed-modality retrieval
AIOpenBMB releases Trident-Qwen3VL-2B, a multimodal embedding model that maps text, images, and fused text-image inputs into one shared space for mixed-modality retrieval. It is fine-tuned from Qwen3-VL-2B-Instruct on Trident-Train, with the LoRA adapter already merged. The Trident-specific weights are released under the MIT License, while the base model's Apache-2.0 terms still apply.
Heat trend
Not enough continuous observations to show a trend yet.