mistral-7b-instruct-v0.2-ov

mistral-7b-instruct-v0.2-ov is an OpenVino int4 quantized version of mistral-7b-instruct-v0.2, providing a fast inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.

mistral-7b-instruct-v0.2 is a popular open source 7b instruct release from Mistral from early 2024.

Model Description

• Developed by: mistralai
• Quantized by: llmware
• Model type: mistral-7b-v0.2
• Parameters: 7 billion
• Model Parent: mistralai/Mistral-7B-Instruct-v0.2
• Language(s) (NLP): English
• License: Apache 2.0
• Uses: General use
• Quantization: int4

Model Card Contact

llmware on github

llmware on hf

llmware website