bling-phi-3-onnx

bling-phi-3-onnx is a fast and accurate fact-based question-answering model, designed for retrieval augmented generation (RAG) with complex business documents, quantized and packaged in ONNX int4 for AI PCs using Intel GPU, CPU and NPU.

This model is one of the most accurate in the BLING/DRAGON model series, which is especially notable given the relatively small size and is ideal for use on AI PCs and local inferencing.

Model Description

• Developed by: llmware
• Model type: phi-3
• Parameters: 3.8 billion
• Quantization: int4
• Model Parent: llmware/bling-phi-3
• Language(s) (NLP): English
• License: Apache 2.0
• Uses: Fact-based question-answering, RAG
• RAG Benchmark Accuracy Score: 99.5

Model Card Contact

llmware on github
llmware on hf
llmware website