CaoYongshengcys's repositories
knowledge-garden
我的第二大脑 second brain，我的数字花园 digital garden，用obsidian双链笔记软件写作而成
MemGPT
Create LLM agents with long-term memory and custom tools 📚🦙
gpt_academic
为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。
CTFd
CTFs as you need them
frp
A fast reverse proxy to help you expose a local server behind a NAT or firewall to the internet.
rethink
A new way to Rethink your notes. A note/thought taking app
llm-viz
3D Visualization of an GPT-style LLM
3D-LLM
Code for 3D-LLM: Injecting the 3D World into Large Language Models
InstantID
InstantID : Zero-shot Identity-Preserving Generation in Seconds 🔥
facechain
FaceChain is a deep-learning toolchain for generating your Digital-Twin.
excelCPU
16-bit CPU for Excel, and related files
Digital
A digital logic designer and circuit simulator.
transferlearning
Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习
Talk-to-papers-RAG
Retrieval Augmented Generation for LLMs to Interact with ArXiv Papers
drawio
draw.io is a JavaScript, client-side editor for general diagramming.
MedicalGPT
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练、有监督微调、RLHF(奖励建模、强化学习训练)和DPO(直接偏好优化)。
Electronic-Forensic-SFT-Dataset
High-quality Electronic Forensic SFT Dataset
ER-NeRF
[ICCV'23] Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis
clash_for_android
ClashForAndroid 备份文件
UltraChat
Large-scale, Informative, and Diverse Multi-round Chat Data (and Models)
Qwen
The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
llama.cpp
Port of Facebook's LLaMA model in C/C++
agents
An Open-source Framework for Autonomous Language Agents
ChatGLM-Efficient-Tuning
Fine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调
baby-llama2-chinese
用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.
hackrf
low cost software radio platform
akcio
Akcio is a demonstration project for Retrieval Augmented Generation (RAG). It leverages the power of LLM to generate responses and uses vector databases to fetch relevant documents to enhance the quality and relevance of the output.
Baichuan-7B
A large-scale 7B pretraining language model developed by BaiChuan-Inc.