Stars
让 Claude Science 一键接入 DeepSeek、硅基流动 Kimi、OpenAI 等第三方 API 的 macOS 本地代理与安装器
An Open Foundation Model and Benchmark to Accelerate Generative Recommendation
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Unified data lake of 293M scientific papers from 8 scholarly sources + 13 ontologies (960 GB Parquet, queryable via DuckDB)
Econ-Embeddings: Semantic Representations of Economic Classification Systems
0 - 1 learn OpenClaw: sections to build an claw-AI agent from scratch
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
This is python utilities library built for greendelta's openLCA. It is used for programmatically calculating the life cycle analysis of process following the ISO 14040/ 14044 standards. It interrea…
Expandable Datasets for Earth Observation
A `dbt` project to analyze data snapshots from OpenAlex
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
company name parser, extract company name brand. 中文公司名称分词工具，支持公司名称中的地名，品牌名（主词），行业词，公司名后缀提取。
Project for a general described class for bipartite (multipartite) Stochastic Block Model
CaML: Carbon Footprinting of Household Products with Zero-Shot Semantic Text Similarity
Scalable joint species distribution modeling
Zonal statistics to aggregate earth engine Images / ImageCollections to shapefiles / Earth Engine FeatureCollections.
An open-source tool for calculating and reporting spatial indicators for healthy, sustainable cities worldwide using open or custom data.
A tour through recommendation algorithms in python [IN PROGRESS]
《可解释的机器学习--黑盒模型可解释性理解指南》，该书为《Interpretable Machine Learning》中文版
How to use the VIIRS satellite data for night time lights.
中国大陆 31 个省份最近几日新增工商企业注册信息以及其他部分企业数据，大概100余万信息，包含企业名称、注册地址、统一社会信用代码、省份、城市、注册日期、经营范围、负责人、邮箱、注册资金、企业类型等资料。 In 31 provinces in mainland China, About 1000000 messages，new business registration informati…