Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

Low ReSource Reinforcement Learning with CPU Offloading Training Support

DigitalPlat FreeDomain: Free Domain For Everyone

Automatic Sketch Colorization with reference image

百度百科爬虫

The most comprehensive online Dify tutorial, powered by FirstLab.

个人年终总结

Official Code for "Coser: Coordinating LLM-Based Persona Simulation of Established Roles"

The paper list of the 86-page SCIS cover paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.

Chat凉宫春日, An open sourced Role-Playing chatbot Cheng Li, Ziang Leng, and others.

淘宝抢购脚本

Hierarchical Attention Networks for document classification

CNNs for Sentence Classification in PyTorch

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Code for ACL 2021 paper "ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information"

Production-ready platform for agentic workflow development.

dify前端二次开发（直接基于原本页面），初次尝试

适配 dify API 的纯 web 前端工程

用vue 开发的 html chatgpt对话框 模板 (参考市面最好看的界面）

服务端：Git开源项目Dify，前端：Dify-web。是我自己结合AI开发的一个web应用，目前支持：流式输出、文字转语音、markdown、上下文持续对话。其它功能接口待补充，欢迎一起学习交流完善！

基于Vue 3和TypeScript构建的智能搜索对话应用前端项目，后端通过Dify工作流编排的对话型应用提供API支持。

中文常用停用词表（哈工大停用词表、百度停用词表等）

Llama中文社区，实时汇总最新Llama学习资料，构建最好的中文Llama大模型开源生态，完全开源可商用

中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models)

数据采集可视化大屏

基于 Flask 和 EChart 的可视化大屏，通过爬虫获取懂车帝数据并存储在MySQL数据库

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

Official Tensorflow implementation of U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation (ICLR 2020)

[ECCV 2020 Spotlight] A Simple and Versatile Framework for Image-to-Image Translation