Run a <400ms latency Voice Agent on just 4GB VRAM. Fully offline, no API keys required. Optimized for GTX 1650 and edge robotics with zero-copy inference. (Apache 2.0)
-
Updated
May 24, 2026 - Python
Run a <400ms latency Voice Agent on just 4GB VRAM. Fully offline, no API keys required. Optimized for GTX 1650 and edge robotics with zero-copy inference. (Apache 2.0)
Lightweight cross-encoder reranker for e-commerce search, fine-tuned on Amazon ESCI. Same size as the baseline, measurably better.
Fine-tuned multilingual MiniLM on 8K Hindi-English pairs via contrastive learning. Recall@1: 75.75% → 85.10% (+9.35pp). UMAP · MRR · Error Analysis.
Bio-inspired adapters that improve foundation models beyond LoRA fine-tuning. 50+ neuroscience mechanisms searched via Thompson sampling over 10²² configurations. Validated on 20 benchmarks (85% win rate). Includes AI bias detection across major models.
Add a description, image, and links to the sentence-transformers-finetune topic page so that developers can more easily learn about it.
To associate your repository with the sentence-transformers-finetune topic, visit your repo's landing page and select "manage topics."