panyang's Stars
langgenius/dify
Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.
karpathy/LLM101n
LLM101n: Let's build a Storyteller
rasbt/LLMs-from-scratch
Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step
ManimCommunity/manim
A community-maintained Python framework for creating mathematical animations.
yanue/V2rayU
V2rayU,基于v2ray核心的mac版客户端,用于科学上网,使用swift编写,支持trojan,vmess,shadowsocks,socks5等服务协议,支持订阅, 支持二维码,剪贴板导入,手动配置,二维码分享等
unslothai/unsloth
Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
graphdeco-inria/gaussian-splatting
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
magic-research/magic-animate
[CVPR 2024] MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model
NVIDIA/TensorRT-LLM
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
colmap/colmap
COLMAP - Structure-from-Motion and Multi-View Stereo
yihong0618/bilingual_book_maker
Make bilingual epub books Using AI translate
aigc-apps/sd-webui-EasyPhoto
📷 EasyPhoto | Your Smart AI Photo Generator.
qiuyu96/CoDeF
[CVPR 2024 Highlight] Official PyTorch implementation of CoDeF: Content Deformation Fields for Temporally Consistent Video Processing
Zejun-Yang/AniPortrait
AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation
modelscope/ms-swift
Use PEFT or Full-parameter to finetune 350+ LLMs or 90+ MLLMs. (LLM: Qwen2.5, Llama3.2, GLM4, Internlm2.5, Yi1.5, Mistral, Baichuan2, DeepSeek, Gemma2, ...; MLLM: Qwen2-VL, Qwen2-Audio, Llama3.2-Vision, Llava, InternVL2, MiniCPM-V-2.6, GLM4v, Xcomposer2.5, Yi-VL, DeepSeek-VL, Phi3.5-Vision, ...)
OpenDroneMap/WebODM
User-friendly, commercial-grade software for processing aerial imagery. 🛩
Huanshere/VideoLingo
Netflix级字幕切割、翻译、对齐、甚至加上配音，一键全自动视频搬运AI字幕组
Chenyme/Chenyme-AAVT
这是一个全自动（音频）视频翻译项目。利用Whisper识别声音，AI大模型翻译字幕，最后合并字幕视频，生成翻译后的视频。
mjpost/sacrebleu
Reference BLEU implementation that auto-downloads test sets and reports a version string to facilitate cross-lab comparisons
zxyle/PDF-Explained
《PDF 解析》
lizhe2004/Awesome-LLM-RAG-Application
the resources about the application based on LLM with RAG pattern
LetheSec/HuggingFace-Download-Accelerator
利用HuggingFace的官方下载工具从镜像网站进行高速下载。
jonbarron/camp_zipnerf
QPromise/EasyTrans
支持谷歌翻译、百度翻译、有道翻译的免费接口，基于Django、PyMuPDF实现了pdf文档英译汉的功能，翻译后的pdf格式基本保持不变，可以下载docx和pdf格式的翻译文档，基本解决复制caj中文论文时的格式问题，简单的满足看论文以及写总结的需求。
TUDB-Labs/mLoRA
An Efficient "Factory" to Build Multiple LoRA Adapters
hsing-wang/Awesome-LLM-MT
Ding-Kyoma/EasyTrans-mac
PDF 批量翻译，翻译后的PDF格式基本不变。导出PDF和Docx。优化并精简了来自于QPromise 的 EasyTrans。优化了通过百度翻译API稳定进行长翻译！
ecnu-sea/SEA
SEA is an automated paper review framework capable of generating comprehensive and high-quality review feedback with high consistency for papers, thereby assisting researchers in improving the quality of their work.
SeaseLtd/vector-search-elastic-tutorial
Text Embeddings and Vector Search with Elasticsearch and Open-Source Technologies
SXU-YaxinGuo/CRMU
儿童故事常识推理与寓意理解评测（Commonsense Reasoning and Moral Understanding Evaluation in Children's Stories，CRMU）