tencent/EVIE-Preview-4.5B · Hugging Face
英文标题：tencent/EVIE-Preview-4.5B · Hugging Face
Overview EVIE-Preview-4.5B is a state-of-the-art multilingual Visual Document Retrieval (VDR) model built upon Qwen3.5-4B. It employs ColBERT-style late interaction with native 128-dimensional multi-vector token embeddings (4.54B parameters, BF16). By combining native GatedDeltaNet linear-atte
打开原文相关 3 · 机会 0
中文
Overview EVIE-Preview-4.5B is a state-of-the-art multilingual Visual Document Retrieval (VDR) model built upon Qwen3.5-4B. It employs ColBERT-style late interaction with native 128-dimensional multi-vector token embeddings (4.54B parameters, BF16). By combining native GatedDeltaNet linear-atte
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
Overview EVIE-Preview-4.5B is a state-of-the-art multilingual Visual Document Retrieval (VDR) model built upon Qwen3.5-4B. It employs ColBERT-style late interaction with native 128-dimensional multi-vector token embeddings (4.54B parameters, BF16). By combining native GatedDeltaNet linear-atte