Vocabulary-Qwen3-VL-Embedding-2B

UPShf/Vocabulary-Qwen3-VL-Embedding-2B

Vocabulary-Qwen3-VL-Embedding-2B is a feature extraction model from UPShf. Use it when you need embeddings to search or compare text. The card lists the license as apache-2.0.

This repository contains precalculated Feature Extraction matrices (embeddings) designed for Sigma-Captioner. These caches allow for high-speed image-to-text alignment and similarity searching without re-encoding the…

Downloads · 30 days

Access

Public

Updated Apr 1, 2026

Repo size

9 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.pt6.1 GB · 100%

At a glance

Task: Feature Extraction
License: apache-2.0
Access: Public
Created: Mar 27, 2026
Updated: Apr 1, 2026
SHA: fdc28b8d

Base models

Qwen/Qwen3-VL-Embedding-2B

Model card

From the Hugging Face model README

About

This repository contains precalculated Feature Extraction matrices (embeddings) designed for Sigma-Captioner. These caches allow for high-speed image-to-text alignment and similarity searching without re-encoding the entire vocabulary on every run.

Compatible with any project, but recommended for use with https://github.com/uninterruptedpowersupply3-NEW/Sigma-Captioner/tree/SGLANG

📊 Dataset Sources

English: dwyl/english-words
Anime/Visual: cagliostrolab/860k-ordered-tags-json (Danbooru tags)

📂 Directory Structure & Usage

The embeddings are split into two versions based on reliability:

Path	Contents	Recommendation
`root/`	`vocab_hybrid_matrix.pt`	Base Use: Stable and recommended for general tasks.
`DANANDENG/`	`vocab_hybrid_meta.pt`	Experimental: Hybrid Anime + English merge.

[!WARNING]
Experimental Warning: The Anime tags in the DANANDENG directory are prone to hallucinations regarding specific characters. Use the root files for production/standard tagging and reserve the DANANDENG files for experimental research.

Model: Qwen/Qwen3-VL-Embedding-2B
Format: PyTorch Tensor (.pt) + JSON Metadata

Task: Feature Extraction
License: apache-2.0
Created: Mar 27, 2026
Updated: Apr 1, 2026