Instructions to use HIT-TMG/JevEmbed-Qwen3-Embedding-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use HIT-TMG/JevEmbed-Qwen3-Embedding-4B with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("HIT-TMG/JevEmbed-Qwen3-Embedding-4B") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
Download NOTICE from HIT-TMG/JevEmbed-Qwen3-Embedding-4B: direct link, hf CLI and curl.
- Browser
- Download file 310 Bytes
-
https://huggingface.co/HIT-TMG/JevEmbed-Qwen3-Embedding-4B/resolve/main/NOTICE
- Command line
-
hf download hf://HIT-TMG/JevEmbed-Qwen3-Embedding-4B/NOTICE
-
curl -L -o NOTICE https://huggingface.co/HIT-TMG/JevEmbed-Qwen3-Embedding-4B/resolve/main/NOTICE
310 Bytes
| JevEmbed-Qwen3-Embedding-4B | |
| Based on Qwen/Qwen3-Embedding-4B, licensed under Apache License 2.0. | |
| Qwen source model: https://huggingface.co/Qwen/Qwen3-Embedding-4B | |
| The LoRA adapter was trained on HIT-TMG/JevEmbed-Data and merged into the base model. | |
| Dataset source licenses vary; see the dataset source report. | |