You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Vietnamese Product E5 Small

Fine-tuned SentenceTransformer model for asymmetric Vietnamese product retrieval: short search queries are matched to longer product documents.

Base model

intfloat/multilingual-e5-small

Usage

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("trantuan1701/product-e5-small-vietnamese")

query_embeddings = model.encode(
    ["query: đèn led downlight at02 đổi màu"],
    normalize_embeddings=True,
)

document_embeddings = model.encode(
    ["passage: product document text..."],
    normalize_embeddings=True,
)

Important: this E5 model expects query: for queries and passage: for documents.

Training summary

Loss: MultipleNegativesRankingLoss
Max sequence length: 512
Dataset: 15,000 query-document pairs, 1,000 product documents
Validation split: deterministic by doc_id

Limitations

Current validation loss is a training diagnostic only. A full retrieval benchmark should report Recall@K, MRR, and NDCG before production selection.

Downloads last month: 45

Safetensors

Model size

0.1B params

Tensor type

F32