Instructions to use xCloudinfo/xVITA-Embed-300M-zhTW-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use xCloudinfo/xVITA-Embed-300M-zhTW-GGUF with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf xCloudinfo/xVITA-Embed-300M-zhTW-GGUF:Q8_0 # Run inference directly in the terminal: llama cli -hf xCloudinfo/xVITA-Embed-300M-zhTW-GGUF:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf xCloudinfo/xVITA-Embed-300M-zhTW-GGUF:Q8_0 # Run inference directly in the terminal: llama cli -hf xCloudinfo/xVITA-Embed-300M-zhTW-GGUF:Q8_0
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf xCloudinfo/xVITA-Embed-300M-zhTW-GGUF:Q8_0 # Run inference directly in the terminal: ./llama-cli -hf xCloudinfo/xVITA-Embed-300M-zhTW-GGUF:Q8_0
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf xCloudinfo/xVITA-Embed-300M-zhTW-GGUF:Q8_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf xCloudinfo/xVITA-Embed-300M-zhTW-GGUF:Q8_0
Use Docker
docker model run hf.co/xCloudinfo/xVITA-Embed-300M-zhTW-GGUF:Q8_0
- LM Studio
- Jan
- Ollama
How to use xCloudinfo/xVITA-Embed-300M-zhTW-GGUF with Ollama:
ollama run hf.co/xCloudinfo/xVITA-Embed-300M-zhTW-GGUF:Q8_0
- Unsloth Studio
How to use xCloudinfo/xVITA-Embed-300M-zhTW-GGUF with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for xCloudinfo/xVITA-Embed-300M-zhTW-GGUF to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for xCloudinfo/xVITA-Embed-300M-zhTW-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for xCloudinfo/xVITA-Embed-300M-zhTW-GGUF to start chatting
- Atomic Chat new
- Docker Model Runner
How to use xCloudinfo/xVITA-Embed-300M-zhTW-GGUF with Docker Model Runner:
docker model run hf.co/xCloudinfo/xVITA-Embed-300M-zhTW-GGUF:Q8_0
- Lemonade
How to use xCloudinfo/xVITA-Embed-300M-zhTW-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull xCloudinfo/xVITA-Embed-300M-zhTW-GGUF:Q8_0
Run and chat with the model
lemonade run user.xVITA-Embed-300M-zhTW-GGUF-Q8_0
List all available models
lemonade list
xVITA-Embed-300M-zhTW — GGUF
xCloudinfo/xVITA-Embed-300M-zhTW(云碩科技自製繁體中文檢索 embedding,DRCD test hit@1 86.0、超越 bge-m3 / multilingual-e5-large)的 GGUF 量化版,適用 llama.cpp 與 ollama。
2026-07-18 重要修復:本日以前的所有 GGUF 檔因轉檔工具與 sentence-transformers 5.6 模組命名不相容, 缺少模型的 Dense 投影層,向量空間與 safetensors 版不一致(cosine 相似度失效)。請重新下載本日後的檔案。 現版本已逐一與 safetensors 版驗證向量一致(f16 cosine = 1.0、Q8_0 = 0.9998),並已把 mean pooling 寫入 GGUF metadata,llama.cpp 無須再手動指定
--pooling。
兩種版本,依場景選
| 版本 | context | 檔案 | 大小 | 適用 |
|---|---|---|---|---|
| 標準版(v2) | 8192 | xcloud-emb-zhtw-f16.gguf | 584 MB | 一般 RAG、段落級檢索(短文分數最佳 86.0) |
| xcloud-emb-zhtw-Q8_0.gguf | 313 MB | |||
| 長文特化版 | 8192 | xcloud-emb-zhtw-8k-f16.gguf | 584 MB | 長文件整篇檢索、法規/報告全文(長文分數最佳 84.7) |
| xcloud-emb-zhtw-8k-Q8_0.gguf | 313 MB |
- 段落級 RAG(chunk ≤ 2048 tokens)用標準版,短文檢索分數最佳。
- 把整份長文件當單一檢索單位(整篇法規、報告全文)用長文特化版。
- 兩版皆 768 維、同一 prompt 格式、皆支援 8192 tokens 輸入;差別在訓練取向(標準版短文最佳、長文特化版長文最佳)。
- Q8_0 幾乎無損(與 f16 cosine 0.9998)、體積小一半,一般首選。
評測(DRCD test,與 safetensors 版同 protocol)
短段落檢索(3,493 查詢 / 1,000 段落庫):
| 模型 | hit@1 | hit@5 | hit@10 |
|---|---|---|---|
| 標準版 v2(0.3B) | 86.0 | 97.4 | 98.7 |
| multilingual-e5-large(0.56B) | 82.8 | 95.3 | 97.0 |
| BAAI/bge-m3(0.57B) | 82.2 | 95.6 | 97.2 |
長文整篇檢索(378 篇完整文章 / 3,493 查詢):
| 模型 | hit@1 | hit@5 | hit@10 |
|---|---|---|---|
| 長文特化版 | 84.7 | 94.5 | 96.6 |
| 標準版 v2 | 79.2 | 91.2 | 94.3 |
| BAAI/bge-m3(8k 原生) | 77.5 | 90.3 | 93.4 |
長文特化版在完整文章檢索上勝過 bge-m3 原生 8k 達 7.2 個百分點。
llama.cpp
# 標準版(段落級 RAG)
llama-server -m xcloud-emb-zhtw-Q8_0.gguf --embeddings --port 8080
# 長文特化版(整篇長文件檢索)
llama-server -m xcloud-emb-zhtw-8k-Q8_0.gguf --embeddings --port 8080
查詢端與文檔端請使用 EmbeddingGemma 規格 prompt:
- 查詢:
task: search result | query: {你的問題} - 文檔:
title: none | text: {文檔內容}
完整評測、訓練細節與誠實聲明見主 repo model card。
云碩科技股份有限公司(xCloudinfo Corp. Limited)
授權
底模依 Gemma Terms of Use 授權,本量化模型之使用同受其約束。
Gemma 合規聲明
Gemma is provided under and subject to the Gemma Terms of Use found at ai.google.dev/gemma/terms
- 本模型為 Google EmbeddingGemma-300m 的修改版本(Model Derivative),經繁體中文檢索語料微調後轉換為 GGUF 格式。
- 使用者再散布本模型或其衍生物時,須一併傳遞 Gemma Terms of Use 第 3.2 節之使用限制。
註:GGUF 檔名維持
xcloud-emb-*前綴不變,以免既有下載腳本與 ollama 設定失效;模型本身即 xVITA-Embed-300M-zhTW。
- Downloads last month
- 655
8-bit
16-bit
Model tree for xCloudinfo/xVITA-Embed-300M-zhTW-GGUF
Base model
google/embeddinggemma-300m
docker model run hf.co/xCloudinfo/xVITA-Embed-300M-zhTW-GGUF:Q8_0