doberst's picture
Update README.md
7e0ec39 verified
metadata
license: apache-2.0
inference: false
base_model: Qwen/Qwen2-7B-Instruct
base_model_relation: quantized
tags:
  - green
  - p7
  - llmware-chat
  - ov

qwen-2-7b-instruct-ov

qwen-2-7b-instruct-ov is an OpenVino int4 quantized version of Qwen2 7b Instruct, providing a very fast, very small inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.

qwen-2-7b-instruct-ov is a leading chat model known for its high accuracy and strong math and logical capabilities.

Model Description

  • Developed by: Qwen
  • Quantized by: llmware
  • Model type: qwen2-7b-instruct
  • Parameters: 7 billion
  • Model Parent: Qwen/Qwen2-7B-Instruct
  • Language(s) (NLP): English
  • License: Apache 2.0
  • Uses: General purpose chat
  • RAG Benchmark Accuracy Score: NA
  • Quantization: int4

Model Card Contact

llmware on github

llmware on hf

llmware website