Edit model card

dragon-yi-6b-ov

dragon-yi-6b-ov is an OpenVino int4 quantized version of DRAGON Yi 6b v1.5, providing a fast inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.

dragon-yi-6b is a fact-based question-answering model, optimized for complex business documents.

This is a very accurate model, with one of the highest scores on the RAG Benchmark accuracy test.

Model Description

  • Developed by: llmware
  • Model type: 01-ai/yi-v1.5
  • Parameters: 6 billion
  • Model Parent: llmware/dragon-yi-1.5v-6b
  • Language(s) (NLP): English
  • License: Apache 2.0
  • Uses: Fact-based question-answering
  • RAG Benchmark Accuracy Score: 99.5
  • Quantization: int4

Model Card Contact

llmware on github

llmware on hf

llmware website

Downloads last month
25
Inference API
Inference API (serverless) has been turned off for this model.

Model tree for llmware/dragon-yi-6b-ov

Quantized
(1)
this model

Collection including llmware/dragon-yi-6b-ov