Xin Zhang | 张鑫@xinzhangaiNew 1.5B embedding and reranking models 🤩 !!! New choice between Qwen3-embedding-0.6B and 4B We release **Lychee-embed** and **Lychee-rerank**, based-on Qwen2.5-1.5B and our multi-stage training framework in COLM 2025 paper. #NLP #LLM #RAG #COLM20257:00 AM · Aug 18, 202518.1KViews235241177
Xin Zhang | 张鑫@xinzhangaiAug 18, 2025Embedding model: huggingface.co/vec-ai/lychee-… Reranking model: huggingface.co/vec-ai/lychee-… Github: github.com/vec-ai/lychee-…16526
