libintc123
Follow
Stars
中文对话0.2B小模型（ChatLM-Chinese-0.2B），开源所有数据集来源、数据清洗、tokenizer训练、模型预训练、SFT指令微调、RLHF优化等流程的全部代码。支持下游任务sft微调，给出三元组信息抽取微调示例。
🚀 「大模型」1小时从0训练26M参数的视觉多模态VLM！🌏 Train a 26M-parameter VLM from scratch in just 1 hours!
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!
Perplexity style AI Search engine clone built with Gemini 2.0 Flash and Grounding
A library to build 3D human characters in the browser
3D Loader using three js : https://hmthanh.github.io/3d-human-model/
Editing Animated 3D Human Textures with Instructions
Open source AI analyst powered by E2B. Analyze your CSV files with Llama 3.1 and create interactive charts.
AI tool to build charts based on text input
PlotAI - Your Ultimate Plotting Assistant! 📊🤖 Use ChatGPT-3.5 to create plots in Python and Matplotlib directly in your Python script or notebook.
AI 智能生成 PPT，通过主题/文件/网址等方式生成PPT，支持原生图表、动画、3D特效等复杂PPT的解析和渲染，支持用户自定义模板，支持智能添加动画，可在线体验。AI generates PowerPoint Presentation, Supports parsing and rendering of complex PPT features such as native charts…
Generate charts using OpenAI Code Interpreter
使用labelImg对水印位置进行标注，ultralytics-YOLO8对水印位置进行模型训练&检测。
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO、GRPO。
Training and generation / detection / inference scripts dealing with Yolov8
Watermark remover from D-Ogi/WatermarkRemover-AI
Image restoration with neural networks but without learning.
[AAAI 2025] EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning
a machine learning image inpainting task that instinctively removes watermarks from image indistinguishable from the ground truth image
Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.
基于AI的图片/视频硬字幕去除、文本水印去除，无损分辨率生成去字幕、去水印后的图片/视频文件。无需申请第三方API，本地实现。AI-based tool for removing hard-coded subtitles and text-like watermarks from videos or Pictures.
An unofficial and partial Keras implementation of "Noise2Noise: Learning Image Restoration without Clean Data"
前端监控，性能监控平台。前端监控平台专注于Web端体验数据监控。对网页健康状况的三个方面进行监测：页面打开速度（速度测量）、页面稳定性（JS错误）和外部服务调用成功率（API）
AI video editor that convert long videos to short clips
基于pytorch实现的图片分类模型训练框架，各个部分模块化，方便修改模型。包含分类模型、训练、验证、测试、剪枝再训练、wandb可视化、onnx导出、onnx推理、tensorrt导出、tensorrt推理、部署。
MuCGEC中文纠错数据集及文本纠错SOTA模型开源；Code & Data for our NAACL 2022 Paper "MuCGEC: a Multi-Reference Multi-Source Evaluation Dataset for Chinese Grammatical Error Correction"