AITeamVN/Vi-Qwen2-3B-RAG
TEXT GENERATIONConcurrency Cost:1Model Size:3.1BQuant:BF16Ctx Length:32kPublished:Oct 1, 2024License:apache-2.0Architecture:Transformer0.0K Open Weights Warm

AITeamVN/Vi-Qwen2-3B-RAG is a 3.1 billion parameter language model, fine-tuned from the Qwen2-Instruct base model, specifically optimized for Retrieval Augmented Generation (RAG) tasks in Vietnamese. It excels at extracting useful information from noisy documents, rejecting answers when information is absent, integrating information from multiple documents, and accurately identifying positive/negative contexts. This model is designed to enhance Vietnamese language processing capabilities and improve RAG performance, supporting context lengths up to 8192 tokens.

Loading preview...