dragon-llama2-ov / README.md
doberst's picture
Upload 11 files
9bd4806 verified
|
raw
history blame
1.17 kB
metadata
license: llama2
inference: false
tags:
  - green
  - llmware-rag
  - p7
  - ov

dragon-llama-2-ov

dragon-llama-2-ov is an OpenVino int4 quantized version of Dragon Llama-2, providing a very fast, very small inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.

dragon-llama-2 is a fact-based question-answering model, optimized for complex business documents.

Get started right away with OpenVino

Looking for AI PC solutions and demos, contact us at llmware

Model Description

  • Developed by: llmware
  • Model type: llama2
  • Parameters: 7 billion
  • Model Parent: llmware/dragon-llama-2-v0
  • Language(s) (NLP): English
  • License: llama2-community-license
  • Uses: Fact-based question-answering
  • RAG Benchmark Accuracy Score: 97.25
  • Quantization: int4

Model Card Contact

llmware on hf

llmware website