MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.
An open-source implementaion for fine-tuning Pixtral by MistralAI.
Examples of Mistral API using Python REST / curl
RevealVLLMSafetyEval is a comprehensive pipeline for evaluating Vision-Language Models (VLMs) on their compliance with harm-related policies. It automates the creation of adversarial multi-turn datasets and the evaluation of model responses, supporting responsible AI development and red-teaming efforts.
LoRA-based fine-tuning pipeline for Pixtral‑12B on multimodal instruction tasks using Hugging Face and vision-language templates.
a voice-controlled operating system
Pixtral Streamlit Demo App
LookOutAI is a tool for spotting a target person across images or video clips using facial recognition. It leverages NLP and LLMs to describe appearances and includes features to censor or highlight the target’s face.
Add a description, image, and links to the pixtral topic page so that developers can more easily learn about it.
To associate your repository with the pixtral topic, visit your repo's landing page and select "manage topics."