Hugging Face's logo
Kim's picture
1 1 17

Kim

ilyoung
IniNLP247's profile picture
·

AI & ML interests

Researcher for Blockchain & Avatar Services

Recent Activity

liked a dataset about 1 month ago
fka/awesome-chatgpt-prompts
reacted to yeonseok-zeticai's post with 🤗 3 months ago
⚡ ColBERT-ko-v1.0 Complete On-device Study: SOTA Korean Retrieval on Mobile Major Release: Comprehensive mobile deployment study of yoonjong's ColBERT-ko-v1.0 with detailed performance benchmarks across 50+ mobile devices! 🎯 Model Overview: Architecture: Korean-optimized ColBERT (late interaction) Parameters: 0.1B (compact and efficient) Specialty: Korean document retrieval and semantic search Performance: 1.0 recall@10, 0.966 nDCG@10 on AutoRAGRetrieval Benchmark: Outperforms Jina-ColBERT-v2 on Korean MTEB tasks 📊 Mobile Performance Results: Latency Metrics: NPU (Best): 3.17ms average inference GPU: 11.67ms average CPU: 21.36ms average NPU Advantage: 18.46x speedup over CPU Memory Efficiency: Model Size: 567.89 MB (production optimized) Runtime Memory: 170.87 MB peak consumption Load Range: 4-614 MB across device categories FP32 Memory: 642.65 MB (optional high precision) Accuracy Preservation: - FP16 Precision: 53.51 dB maintained - Quantized Mode: 32.77 dB (available for memory constraints) -Retrieval Quality: Production-grade Korean semantic matching 🔬 Research Implications: This study demonstrates: - Late interaction models are viable for mobile deployment - Korean language models achieve SOTA performance on consumer hardware - Sub-5ms retrieval enables real-time RAG applications - Privacy-first Korean AI is now technically feasible Benchmark Methodology: - Standardized Korean query inputs - Multiple inference cycles with statistical averaging - Real-world Korean document corpus testing - Thermal and battery impact assessment Deployment Recommendations: - Use NPU acceleration for 18x speedup on Android - Implement MUVERA for real-time requirements - Cache frequent queries for instant responses - Progressive loading for large document collections - Hybrid approach for extremely large corpora (local + cloud) 🔗 Resources: Complete Study: https://mlange.zetic.ai/p/Steve/colbert_kor Original Model: https://huggingface.co/yoonjong0505/ColBERT-ko-v1.0
liked a model 5 months ago
o0dimplz0o/Fine-Tuned-Whisper-Large-v2-Zeroth-STT-KO
View all activity

Organizations

None yet