dragon-mistral-ov

dragon-mistral-ov is a high-quality fact-based question-answering model, designed for retrieval augmented generation (RAG) with complex business documents, quantized and packaged in OpenVino int4 for AI PCs using Intel GPU, CPU and NPU.

This model provides a good combination of quality and inference speed.

Model Description

• Developed by: llmware
• Model type: mistral-0.1
• Parameters: 7 billion
• Quantization: int4
• Model Parent: llmware/dragon-mistral-7b-v0
• Language(s) (NLP): English
• License: Apache 2.0
• Uses: Fact-based question-answering, RAG
• RAG Benchmark Accuracy Score: 96.5

Model Card Contact

llmware on github
llmware on hf
llmware website