Starred repositories
主要记录大语言大模型(LLMs) 算法(应用)工程师相关的知识及面试题
AIGC-interview/CV-interview/LLMs-interview面试问题与答案集合仓,同时包含工作和科研过程中的新想法、新问题、新资源与新项目
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch and FLAX.
Enjoy the magic of Diffusion models!
本项目旨在分享大模型相关技术原理以及实战经验(大模型工程化、大模型应用落地)
Accelerating the development of large multimodal models (LMMs) with one-click evaluation module - lmms-eval.
Official Implementation of WACV 2023 paper "3D GAN Inversion with Pose Optimization".
DISC-FinLLM,中文金融大语言模型(LLM),旨在为用户提供金融场景下专业、智能、全面的金融咨询服务。DISC-FinLLM, a Chinese financial large language model (LLM) designed to provide users with professional, intelligent, and comprehensive financ…
A pure python based utility to extract text and images from docx files.
[AAAI 2023] Exploring CLIP for Assessing the Look and Feel of Images
Datawhale成员整理的面经,内容包括机器学习,CV,NLP,推荐,开发等,欢迎大家star
Firefly中文LLaMA-2大模型,支持增量预训练Baichuan2、Llama2、Llama、Falcon、Qwen、Baichuan、InternLM、Bloom等大模型
中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models)
Official code for Goldfish model for long video understanding and MiniGPT4-video for short video understanding
[ECCV2024] Video Foundation Models & Data for Multimodal Understanding
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
整理开源的中文大语言模型,以规模较小、可私有化部署、训练成本较低的模型为主,包括底座模型,垂直领域微调及应用,数据集与教程等。
Llama中文社区,实时汇总最新Llama学习资料,构建最好的中文Llama大模型开源生态,完全开源可商用
Detect AI-generated images in an online setting
Code for the paper: CNN-generated images are surprisingly easy to spot... for now https://peterwang512.github.io/CNNDetection/
MiniCPM4: Ultra-Efficient LLMs on End Devices, achieving 5+ speedup on typical end-side chips
Erase specific content from the video that you don't wanna see
视频硬字幕提取,生成srt文件。无需申请第三方API,本地实现文本识别。基于深度学习的视频字幕提取框架,包含字幕区域检测、字幕内容提取。A GUI tool for extracting hard-coded subtitle (hardsub) from videos and generating srt files.
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.
video_summarize(视频总结:上传视频通过prompt对视频内容经行总结输出)