Arjunvad/unified-model-stage1-5-embedding-v2

Arjunvad/unified-model-stage1-5-embedding-v2 is a 3.1 billion parameter model with a 32768 token context length. This model is designed for embedding tasks, providing vector representations of text. Its primary use case is generating high-quality embeddings for applications requiring semantic search, retrieval-augmented generation, or clustering.