lldhliu's Stars
labmlai/annotated_deep_learning_paper_implementations
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
facebookresearch/segment-anything
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
hacksider/Deep-Live-Cam
real time face swap and one-click video deepfake with only a single image
rasbt/LLMs-from-scratch
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
run-llama/llama_index
LlamaIndex is the leading framework for building LLM-powered agents over your data.
lm-sys/FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
2noise/ChatTTS
A generative speech model for daily dialogue.
mem0ai/mem0
The Memory layer for AI Agents
microsoft/graphrag
A modular graph-based Retrieval-Augmented Generation (RAG) system
fishaudio/fish-speech
SOTA Open Source TTS
guidance-ai/guidance
A guidance language for controlling large language models.
microsoft/Bringing-Old-Photos-Back-to-Life
Bringing Old Photo Back to Life (CVPR 2020 oral)
Kanaries/pygwalker
PyGWalker: Turn your pandas dataframe into an interactive UI for visual analysis
vanna-ai/vanna
🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using RAG 🔄.
naklecha/llama3-from-scratch
llama3 implementation one matrix multiplication at a time
datawhalechina/self-llm
《开源大模型食用指南》针对**宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程
NirDiamant/RAG_Techniques
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and contextually rich responses.
k4yt3x/video2x
A machine learning-based video super resolution and frame interpolation framework. Est. Hack the Valley II, 2018.
facebookresearch/segment-anything-2
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Ucas-HaoranWei/GOT-OCR2.0
Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
modelscope/ms-swift
Use PEFT or Full-parameter to finetune 450+ 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, ...).
karpathy/build-nanogpt
Video+code lecture on building nanoGPT from scratch
xfirefly/Airplay-SDK
The Best Airplay SDK supports Airplay Mirroring and AirPlay Casting to a receiver device.
gusye1234/nano-graphrag
A simple, easy-to-hack GraphRAG implementation
codelion/optillm
Optimizing inference proxy for LLMs
codefuse-ai/CodeFuse-muAgent
An Innovative Agent Framework Driven by KG Engine
wp931120/LongChainKBQA
kbqa,langchain,large langauge model, chatgpt
XingYu-Zhong/ChineseStockGPT
A generative AI dialog system that can ask questions about the Chinese stock market.一个可以针对**股市提问的生成式人工智能对话系统
tianchiguaixia/layoutlmv3-chinese
该项目是为了使用layoutlmv3针对中文图片训练和推理。 其中主要解决三个问题： 1.数据标准化成可以的训练数据集格式 2.layoutlmv3-base-chinese 分词修改 2.超过512长度的文本切分和滑窗操作
seanzhang-zhichen/Qwen-WisdomVast
Qwen-WisdomVast is a large model trained on 1 million high-quality Chinese multi-turn SFT data, 200,000 English multi-turn SFT data, and 2,000 single-turn self-cognition data, using the training methods of DORA and LORA+ based on Qwen1.5-7B as the base. Compared to Qwen1.5-7B-Chat, it has improved mathematical abilities by 5.16%, 12.8% on the Human