helen03

llm.c

LLM training in simple, raw C/CUDA

self-refine

LLMs can generate feedback on their work, use it to improve the output, and repeat this process iteratively.

NeuralGenetic

Building and training artificial neural networks (regression or classification) using the genetic algorithm.

bert4torch

An elegent pytorch implement of transformers

Production-Level-Deep-Learning

A guideline for building practical production-level deep learning systems to be deployed in real world applications.

A_survey_and_tools_of_ChatGPT

Some survey and tools of ChatGPT or ChatGPT-Style Model

Read_Bert_Code

Bert源码阅读与讲解(Pytorch版本)-以BERT文本分类代码为例子

annotated-transformer

An annotated implementation of the Transformer paper.

bert

TensorFlow code and pre-trained models for BERT

sentence-transformers

Multilingual Sentence & Image Embeddings with BERT

clip-as-service

🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP

LangChain-Chinese-Getting-Started-Guide

LangChain 的中文入门教程

faiss

A library for efficient similarity search and clustering of dense vectors.

ChatFiles

Document Chatbot — multiple files. Powered by GPT / Embedding.

vectorhub

Quickly and easily build AI website or application by using embeddings!

LangChain-Tutorials-and-Examples

LangChain结合了大型语言模型、知识库和计算逻辑，可以用于快速开发强大的AI应用。这个仓库包含了我对LangChain的学习和实践经验，包括教程和代码案例。让我们一起探索LangChain的可能性，共同推动人工智能领域的进步！

paper-reading

深度学习经典、新论文逐段精读

causal-recsys-public

CTL

A causal tree method (Causal Tree Learn (CTL)) for heterogeneous treatment effects in Python

causal_inference_python_code

Python code for part 2 of the book Causal Inference: What If, by Miguel Hernán and James Robins

SessionAnalytics

SessionAnalytics-用户路径数据分析挖掘框架

RWKV-LM

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

sentencepiece_chinese_bpe

使用sentencepiece中BPE训练中文词表，并在transformers中进行使用。

ETL-PySpark

ETL (Extract, Transform and Load) with the Spark Python API (PySpark) and Hadoop Distributed File System (HDFS)

HADOOP_PySpark_Example

This repository contains SparkTorch on YARN and time series using the Facebook prophet example

Algorithm-Practice-in-Industry

搜索、推荐、广告、用增等工业界实践文章收集（来源：知乎、Datafuntalk、技术公众号）

indiehackers-steps

《独立开发者的艺术》打造最全的独立开发者指南，一人公司。

uniswapv2

关于UniswapV2，所有你需要了解的一切，这里估计一定都有！文档+视频（合约解析部署、前端部署、subgraph解析部署）

smart-contract-best-practices

A guide to smart contract security best practices

solidity-expert

4年打磨-2022年海外一线大厂-以太坊开发教程（a solidity tutorial makes you a dapp expert）WIP