Qwen3-Embedding-4B-ONNX

这是 Qwen/Qwen3-Embedding-4B 的 ONNX 转换版本,用于在浏览器中使用 Transformers.js。

模型详情

• 模型类型: 文本嵌入
• 基础模型: Qwen3-Embedding-4B
• 参数量: 4B
• 嵌入维度: 2560
• 上下文长度: 32K
• MTEB v2 得分: 74.60
• 支持语言: 100+

使用方法 (Transformers.js v3)

import { pipeline } from "@huggingface/transformers";

// Create a feature extraction pipeline
const extractor = await pipeline(
  "feature-extraction",
  "dssjon/Qwen3-Embedding-4B-ONNX",
  {
    dtype: "fp32",
    device: "webgpu", // Use WebGPU for acceleration
  }
);

// Format query with instruction
const taskDescription = "Given a web search query, retrieve relevant passages that answer the query";
const query = `Instruct: ${taskDescription}\nQuery:What is the capital of China?`;

// Generate embedding
const output = await extractor(query, {
  pooling: "last_token",
  normalize: true
});

console.log(output.data); // 2560-dimensional embedding

使用方法 (Python - 原始模型)

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("Qwen/Qwen3-Embedding-4B")

# For queries
query = "What is the capital of China?"
query_embedding = model.encode(query, prompt_name="query")

# For documents (no prompt needed)
document = "The capital of China is Beijing."
doc_embedding = model.encode(document)

转换详情

• ONNX Opset: 14
• 精度: FP32
• 优化: 无 (ONNX Runtime 优化器尚未支持 Qwen3)
• 文件大小: ~15.3 GB

性能

MTEB v2 基准测试得分:

许可证

Apache 2.0 (与基础模型相同)

引用

@article{qwen3embedding2025,
  title={Qwen3 Embedding},
  author={Qwen Team},
  year={2025},
  url={https://huggingface.co/Qwen/Qwen3-Embedding-4B}
}

致谢

• 基础模型: Qwen/Qwen3-Embedding-4B
• 转换工具: Optimum
• 浏览器运行时: Transformers.js