You can deploy this model and start earning money today!

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

Name: Vocabulary-Qwen3-VL-Embedding-2B
Availability: InStock

embeddings

pytorch

feature-extraction

Qwen/Qwen3-VL-Embedding-2B

finetune

apache-2.0

Views

No views yet

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

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

About

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

📊 Dataset Sources

📂 Directory Structure & Usage

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