Downloads · 30 days
11
26% of all-time downloads
ImgSpace/Qwen3-Embedding-0.6B-Int8
Qwen3-Embedding-0.6B-Int8 is a machine learning model from ImgSpace. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Qwen3-Embedding 0.6B 参数量的 Int8 量化 ONNX 版本,用于文本嵌入(embedding)任务。
Downloads · 30 days
11
26% of all-time downloads
All-time downloads
43
Public
Repo size
611 MB
Likes
0
Public
Click a slice to open those files.
.onnx600 MB · 97%
From the Hugging Face model README
Qwen3-Embedding 0.6B 参数量的 Int8 量化 ONNX 版本,用于文本嵌入(embedding)任务。
import onnxruntime as ort
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("你的用户名/Qwen3-Embedding-0.6B-Int8-ONNX")
session = ort.InferenceSession("Qwen3-Embedding-0.6B.int8.onnx")
text = "这是一个测试句子"
inputs = tokenizer(text, return_tensors="np")
outputs = session.run(None, dict(inputs))
embedding = outputs[0] # 通常是 last_hidden_state 或 pooler_output