Stars
VL-JEPA with training-speed optimizations: frozen X-Encoder feature caching, data-pipeline improvements, torchvision video-I/O fix, and a benchmark harness.
jsegov / autoresearch-win-rtx
Forked from karpathy/autoresearchAI agents running research on single-GPU nanochat training automatically
A local Agent-driven LoRA autoresearch tool for guided setup, autonomous tuning, and experiment reporting.
🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models
A standalone Windows desktop application of HEIC to JPG/JPEG/PNG conversion, built with Python+Tkinter
free heic to JPG/JPEG/PNG/WebP converter, runs entirely in your browser
qstock由“Python金融量化”公众号开发，试图打造成个人量化投研分析包，目前包括数据获取（data）、可视化(plot)、选股(stock)和量化回测（策略backtest）模块。 qstock将为用户提供简洁的数据接口和规整化后的金融市场数据。可视化模块为用户提供基于web的交互图形的简单接口； 选股模块提供了同花顺的选股数据和自定义选股，包括RPS、MM趋势、财务指标、资金流模型…
Parameter-efficient finetuning script for Phi-3-vision, the strong multimodal language model by Microsoft.
A multi-voice TTS system trained with an emphasis on quality
This repository collects 100 papers related to negative sampling methods.
推荐系统入门教程，在线阅读地址：https://datawhalechina.github.io/fun-rec/
2 books and related source codes for algorithmic trading.
Integrate cutting-edge LLM technology quickly and easily into your apps
Open Data, more than 50 financial data. 提供超過 50 個金融資料(台股為主)，每天更新 https://finmind.github.io/
Download market data from Yahoo! Finance's API
Causal Inference for the Brave and True的中文翻译版。全部代码基于Python，适用于计量经济学、量化社会学、策略评估等领域。英文版原作者：Matheus Facure
Causal Inference for the Brave and True. A light-hearted yet rigorous approach to learning about impact estimation and causality.
XGo is a programming language that reads like plain English. But it's also incredibly powerful — it lets you leverage assets from C/C++, Go, Python, and JavaScript/TypeScript, creating a unified so…
DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphic…
《数据科学工程实践》一书的Jupyter Notebook库，以及交流园地。
Data science interview questions and answers
Everything I practice about keras for deep learning
A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning …