doberst's picture
Update README.md
486af79 verified
metadata
license: apache-2.0
inference: false
base_model: Qwen/Qwen2-1.5B-Instruct
base_model_relation: quantized
tags:
  - green
  - llmware-chat
  - p1
  - ov
  - emerald

qwen2-1.5b-instruct-ov

qwen2-1.5b-instruct-ov is an OpenVino int4 quantized version of Qwen2-1.5B-Instruct, providing a very fast, very small inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.

This is from the Qwen2 release series from Qwen (summer 2024), and is a very high-quality smaller model.

Model Description

  • Developed by: Qwen
  • Quantized by: llmware
  • Model type: qwen2
  • Parameters: 1.5 billion
  • Model Parent: Qwen/Qwen2-1.5B-Instruct
  • Language(s) (NLP): English
  • License: Apache 2.0
  • Uses: Chat, general-purpose LLM
  • Quantization: int4

Model Card Contact

llmware on github

llmware on hf

llmware website