slim-qa-gen-tiny-ov / README.md
doberst's picture
Update README.md
6c8e8ed verified
metadata
license: apache-2.0
inference: false
base_model: llmware/slim-qa-gen-tiny
base_model_relation: quantized
tags:
  - green
  - p1
  - llmware-fx
  - ov

slim-qa-gen-tiny-ov

slim-qa-gen-tiny-ov is a specialized function calling model that generates a question and answer pair from a context passage.

This is an OpenVino int4 quantized version of slim-qa-gen-tiny, providing a very fast, very small inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.

Model Description

  • Developed by: llmware
  • Model type: tinyllama
  • Parameters: 1.1 billion
  • Model Parent: llmware/slim-qa-gen-tiny
  • Language(s) (NLP): English
  • License: Apache 2.0
  • Uses: Automated generation of question-answer pairs from complex business documents
  • RAG Benchmark Accuracy Score: NA
  • Quantization: int4

Model Card Contact

llmware on github

llmware on hf

llmware website