MaziyarPanahi/Mistral-7B-Instruct-v0.2

MaziyarPanahi/Mistral-7B-Instruct-v0.2 is an instruction-tuned 7 billion parameter large language model, based on the Mistral-7B-v0.2 architecture developed by Mistral AI. This version features an expanded 32k context window and modified RoPE-theta, making it suitable for complex conversational AI and instruction-following tasks. It is designed for developers seeking a powerful yet efficient model for fine-tuned applications.

Warm
Public
7B
FP8
8192
License: apache-2.0
Hugging Face