liangjianshu/multimodal-image-retrieval
ๅคๆจกๆๆฃ็ดขๅฎๆ๏ผๆๅพ่ฏๅซใPrompt ๅทฅ็จใQwen LoRAใEmbeddingGemma 2 ไธ InfoNCE ๅฏนๆฏๅญฆไน ใๅซ็ๅฎๆผ็คบใ่ชๆๆฐๆฎๆฅๅ ฅใ่ฎญ็ป่ฏๆตๅ RAG ๆฃ็ดข็ปไปถๅญฆไน ๆๅใ
Distributed training & inference for multimodal perception: shared embeddings across text, images, video, audio, code & graphs from 64 to 1024 dimensions ๐ผ๏ธ
$ git clone https://github.com/unum-cloud/UForm.gitๅคๆจกๆๆฃ็ดขๅฎๆ๏ผๆๅพ่ฏๅซใPrompt ๅทฅ็จใQwen LoRAใEmbeddingGemma 2 ไธ InfoNCE ๅฏนๆฏๅญฆไน ใๅซ็ๅฎๆผ็คบใ่ชๆๆฐๆฎๆฅๅ ฅใ่ฎญ็ป่ฏๆตๅ RAG ๆฃ็ดข็ปไปถๅญฆไน ๆๅใ
โฒ +4 โ this week
World's fastest and most compact embedded vector database: exact by default, multimodal, local-first, and GPU-accelerated
โฒ +2 โ this week
Offline semantic Text-to-Image and Image-to-Image search on Android powered by quantized state-of-the-art vision-language pretrained CLIP model and ONNX Runtime inference engine
Transformers 3rd Edition
A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
โฒ +13 โ this week
One proximity graph for vector search, sparse products & attention across RAM, VRAM & NVMe, over dense vectors, sequences, shapes & geospatial sets in 14 languages ๐
Data from GitHub ยท snapshot Nov 16, 2026