streamline the fine-tuning process for multimodal models: PaliGemma 2, Florence-2, and Qwen2.5-VL

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

Testing and evaluating the capabilities of Vision-Language models (PaliGemma) in performing computer vision tasks such as object detection and segmentation.

使用LLaMA-Factory微调多模态大语言模型的示例代码 Demo of Finetuning Multimodal LLM with LLaMA-Factory

Use PaliGemma to auto-label data for use in training fine-tuned vision models.

Minimalist implementation of PaliGemma 2 & PaliGemma VLM from scratch

PyTorch implementation of PaliGemma 2

Notes for the Vision Language Model implementation by Umar Jamil

AI-powered tool to convert text from images into your desired language. Gemma vision model and multilingual model are used.

PyTorch implementation of Google’s Paligemma VLM with SigLip image encoder, KV caching, Rotary embeddings and Grouped Query attention . Modular, research-friendly, and easy to extend for experimentation.

A Python, Shell project focusing on Training Process, License, Author, 1. Defect Detection, PaliGemma Multitask.

Image Captioning with PaliGemma 2 Vision Language Model.

PaLiGemma from-scratch implementation

Leverage PaliGemma 2's DOCCI fine-tuned variant capabilities using LitServe.

Leverage PaliGemma 2 mix model variant capabilities using LitServe.

MAESTRO is an AI-powered research application designed to streamline complex research tasks.