Downloads · 30 days
17
19% of all-time downloads
LaraAI-Labs/KURE-v1-onnx-int8
KURE-v1-onnx-int8 is a machine learning model from LaraAI-Labs. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for onnx. The card lists the license as mit.
nlpai-lab/KURE-v1 (BGE-M3 한국어 파인튜닝)의 ONNX INT8 변환본. 온디바이스(엣지) 한국어 의미검색 임베더용.
Downloads · 30 days
17
19% of all-time downloads
All-time downloads
89
Public
Repo size
591 MB
Likes
0
Public
Click a slice to open those files.
.onnx568 MB · 96%
From the Hugging Face model README
nlpai-lab/KURE-v1 (BGE-M3 한국어 파인튜닝)의
ONNX INT8 변환본. 온디바이스(엣지) 한국어 의미검색 임베더용.
onnxruntime.quantization.quantize_dynamic, QInt8). ~568MB.input_ids, attention_mask (2-input, 동적 batch/seq). 출력: last_hidden_state [batch, seq, 1024].sentencepiece.bpe.model 동봉 — xlm-roberta-large/BGE-M3 와 동일, sha256 cfc8146a…).python export_embedder_onnx.py --model nlpai-lab/KURE-v1 --out ./kure-v1 --dtype int8
torch.onnx.export(legacy, eager attention) → quantize_dynamic(QInt8). 입출력 이름은 소비 C++ 임베더 계약 고정.
원본 nlpai-lab/KURE-v1 (MIT) 의 파생. MIT, 원저작자 표기.