Use PEFT or Full-parameter to finetune 400+ LLMs (Qwen2.5, InternLM3, GLM4, Llama3.3, Mistral, Yi1.5, Baichuan2, DeepSeek-R1, ...) and 150+ MLLMs (Qwen2.5-VL, Qwen2-Audio, Llama3.2-Vision, Llava, InternVL2.5, MiniCPM-V-2.6, GLM4v, Xcomposer2.5, Yi-VL, DeepSeek-VL2, Phi3.5-Vision, GOT-OCR2, ...).

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.

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

【高性能OpenAI LLM服务】通过GPRS+TensorRT-LLM+Tokenizers.cpp实现纯C++版高性能OpenAI LLM服务，支持chat和function call模式，支持ai agent，支持分布式多卡推理，支持多模态，支持gradio聊天界面。

✨🦋 illufly 是自我进化的 Agent 框架: 基于自我进化，快速创造价值

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

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.

视频理解：千问视频多模态模型 & Dify

Colaboratory上でQwenLM/Qwen2-VLをお試しするサンプル

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

Qwen2-VL在文旅领域的LLaMA-Factory微调案例 The case for fine-tuning Qwen2-VL in the field of historical literature and museums

Running Large Language Model easily.

This project demonstrates how to use the Qwen2-VL model from Hugging Face for Optical Character Recognition (OCR) and Visual Question Answering (VQA). The model combines vision and language capabilities, enabling users to analyze images and generate context-based responses.

A workshop for collections of multi-modal LLM examples, samples, reference architecture and demos on Amazon SageMaker.

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

we finetune unsloth llama model to extract mathematical fomulas in the images with optical character recognition(OCR)

"Smart Vision Technology for Quality Control" uses computer vision to automate product inspections, extracting details like product name, quantity, expiry date, and freshness from images. Built for Flipkart Grid 6.0, it enhances accuracy and efficiency in quality control, minimizing manual checks.

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.

A AI- Powered Document organizer tool. It displays a small cute robot on the screen. Give it any file and a small description (optional), It will analyse the contents and description and save it on cloud. When needed, just double click on it, enter the description/keywords for the file you are looking for, It will open the best matching file/