# Mistral Architecture

Based on Microsoft LLaVA-Med v1.5 (Mistral 7B) architecture, customized for Turkish-language medical visual question answering (VQA)

Mini Magnum is a streamlined version of magnum-72b-v1, aiming to replicate the text quality of the Claude 3 series (especially Sonnet and Opus). It is fine-tuned based on Mistral-Nemo-Base-2407, and a new general instruction dataset is added to improve coherence and alignment.

Chewy-Lemon-Cookie-11B is an 11B-parameter large language model based on the Mistral architecture, focusing on text generation and role-playing tasks.

BioMistral-Instructv0.2-7B-DARE is an instruction-tuned model merged using the DARE-TIES method, based on BioMistral/BioMistral-7B and Mistral-7B-Instruct-v0.2, specializing in biomedical domain tasks.

A model fine-tuned based on Vistral-7B-chat, supporting function calling.

Maral is a large language model focused on Persian, built on the Mistral architecture and trained on the Persian Alpaca dataset, while also supporting English generation.

EM German Leo Mistral is a German large language model based on the Mistral architecture, focusing on German text generation tasks.