Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen2.5-VL, Qwen2.5-Omni, Qwen2-Audio, Ovis2, InternVL3, Llava, GLM4v, Phi4, ...) (AAAI 2025).

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

An open-source implementaion for fine-tuning Qwen2-VL and Qwen2.5-VL series by Alibaba Cloud.

Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks, including end-to-end large-scale multi-modal pretrain models and diffusion model toolbox. Equipped with high performance and flexibility.

Higher performance OpenAI LLM service than vLLM serve: A pure C++ high-performance OpenAI LLM service implemented with GPRS+TensorRT-LLM+Tokenizers.cpp, supporting chat and function call, AI agents, distributed multi-GPU inference, multimodal capabilities, and a Gradio chat interface.

Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives

✨🦋 illufly - 【幻蝶】基于记忆蒸馏、资料检索的自我进化智能体

视频理解：千问视频多模态模型 & Dify

A Python base cli tool for caption images with WD series, Joy-caption-pre-alpha,meta Llama 3.2 Vision Instruct and Qwen2 VL Instruct models.

cadrille: Multi-modal CAD Reconstruction with Online Reinforcement Learning

基于多模态大模型的智能搜索助手，通过AI技术实现小红书平台的智能化信息检索和知识整合|An intelligent search assistant based on multimodal large models, enabling smart information retrieval and knowledge integration on the Xiaohongshu platform.

An open-source server implementation for inference Qwen2-VL series model using fastapi.

Official implementation of CMMCoT: Enhancing Complex Multi-Image Comprehension via Multi-Modal Chain-of-Thought and Memory Augmentation

Messy Handwriting OCR Comparison Between Aya-Vision-8B and Qwen2VL-OCR-2B

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.

The Qwen2.5-VL-7B-Instruct model is a multimodal AI model developed by Alibaba Cloud that excels at understanding both text and images. It's a Vision-Language Model (VLM) designed to handle various visual understanding tasks, including image understanding, video analysis, and even multilingual support.

Qwen2.5-VL-Server

A specialized optical character recognition (OCR) application built on advanced vision-language models, designed for document-level OCR, long-context understanding, and mathematical LaTeX formatting. Supports both image and video processing with multiple state-of-the-art model

This repo contains the winning code for Amazon ML Challenge 2024. The challenge was to develop a Machine Learning model to extract product entity details directly from the product images.