Dark Litss (lss233)

lss233

Geek Repo

Company:Tencent

Location:Iceland III

Home Page:https://lss233.com/

Twitter:@lss233_

Github PK Tool:Github PK Tool


Organizations
HMUniversity
RBQUniversity
ThePhoenixMC
typical-motion

Dark Litss's starred repositories

LLaMA-Factory

Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)

Language:PythonLicense:Apache-2.0Stargazers:31856Issues:204Issues:4917

faiss

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

MS-DOS

The original sources of MS-DOS 1.25, 2.0, and 4.0 for reference purposes

Language:AssemblyLicense:MITStargazers:30653Issues:746Issues:0

InstantID

InstantID : Zero-shot Identity-Preserving Generation in Seconds 🔥

Language:PythonLicense:Apache-2.0Stargazers:10741Issues:125Issues:217

mamba

The Fast Cross-Platform Package Manager

Language:C++License:BSD-3-ClauseStargazers:6794Issues:47Issues:1734

draco

Draco is a library for compressing and decompressing 3D geometric meshes and point clouds. It is intended to improve the storage and transmission of 3D graphics.

Language:C++License:Apache-2.0Stargazers:6481Issues:220Issues:699

coroot

Coroot is an open-source APM & Observability tool, a DataDog and NewRelic alternative 📊, 🖥️, 👉. Powered by eBPF for rapid insights into system performance. Monitor, analyze, and optimize your infrastructure effortlessly for peak reliability at any scale.

Language:GoLicense:Apache-2.0Stargazers:5233Issues:39Issues:147

YOLO-World

[CVPR 2024] Real-Time Open-Vocabulary Object Detection

Language:PythonLicense:GPL-3.0Stargazers:4448Issues:40Issues:434

sahi

Framework agnostic sliced/tiled inference + interactive ui + error analysis plots

Language:PythonLicense:MITStargazers:3992Issues:43Issues:0

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(PT)、有监督微调(SFT)、RLHF、DPO、ORPO。

Language:PythonLicense:Apache-2.0Stargazers:3244Issues:38Issues:392

Alpaca-CoT

We unified the interfaces of instruction-tuning data (e.g., CoT data), multiple LLMs and parameter-efficient methods (e.g., lora, p-tuning) together for easy use. We welcome open-source enthusiasts to initiate any meaningful PR on this repo and integrate as many LLM related technologies as possible. 我们打造了方便研究人员上手和使用大模型等微调平台,我们欢迎开源爱好者发起任何有意义的pr!

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:2593Issues:36Issues:100

Chat-Haruhi-Suzumiya

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

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:1784Issues:16Issues:61

tokyo-night-vscode-theme

A clean, dark Visual Studio Code theme that celebrates the lights of Downtown Tokyo at night.

loghub

A large collection of system log datasets for AI-driven log analytics [ISSRE'23]

legado-Harmony

开源阅读鸿蒙版仓库

Language:KotlinLicense:GPL-3.0Stargazers:922Issues:6Issues:7

raptor

The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval

Language:PythonLicense:MITStargazers:877Issues:10Issues:39

zouxian

Permanent Apple Intelligence + Xcode Predictive Code Completion for Chinese-market Mac computers

Language:ShellLicense:MITStargazers:679Issues:6Issues:13

NTTS

NO TIME TO SLEEP

Language:PythonLicense:MITStargazers:639Issues:2Issues:20

ComfyUI-YoloWorld-EfficientSAM

Unofficial implementation of YOLO-World + EfficientSAM for ComfyUI

Language:PythonLicense:GPL-3.0Stargazers:591Issues:6Issues:85

CodeQwen1.5

CodeQwen1.5 is the code version of Qwen, the large language model series developed by Qwen team, Alibaba Cloud.

octopack

🐙 OctoPack: Instruction Tuning Code Large Language Models

Language:Jupyter NotebookLicense:MITStargazers:425Issues:11Issues:20

NeuralFlow

Visualize the intermediate output of Mistral 7B

Language:PythonLicense:GPL-3.0Stargazers:306Issues:8Issues:4

starcoder2-self-align

StarCoder2-Instruct: Fully Transparent and Permissive Self-Alignment for Code Generation

Language:PythonLicense:Apache-2.0Stargazers:221Issues:6Issues:6

awesome-harmony

收录来源于网上鸿蒙系统开发的相关资料

Language:JavaScriptStargazers:160Issues:5Issues:0

LlamaTouch

LlamaTouch: A Faithful and Scalable Testbed for Mobile UI Task Automation

chinese-tokens-in-tiktoken

Chinese tokens in tiktoken tokenizers.

RLHF_PPO

ppo算法实现

Language:PythonLicense:Apache-2.0Stargazers:15Issues:0Issues:0
Language:PythonLicense:MITStargazers:8Issues:0Issues:0

SexyAppFramework

The PopCap game framework, named SexyApp Framework, is a flexible high-level library that provides commonly required functions and reusable components, designed to facilitate rapid development of high-quality games.