Top Trending Github Projects on 04/21/2023: Discovering the Hottest Repositories of the Day!
Projects that have already appeared in previous Github ranking lists will not display details, please refer to previous lists for information.
Rank #1 Stability-AI/StableLM
https://github.com/Stability-AI/StableLM
StableLM: Stability AI Language Models
Language: Jupyter Notebook
Stars: 9,322(2,329 stars today) Forks:445
StableLM is a series of language models developed by Stability AI, which is continuously updated with new checkpoints. These models are trained on a large dataset, The Pile, which contains 1.5 trillion tokens, and will be trained on up to 1.5 trillion tokens. The context length for these models is 4096 tokens. StableLM-Alpha models are available in two sizes, 3B and 7B parameters, and more models are on the way. In addition, StableLM-Tuned-Alpha is a proof-of-concept model that has been fine-tuned with Stanford Alpaca’s procedure using a combination of five recent datasets for conversational agents. The models are available under the CC BY-SA-4.0 license and can be used in various fields, such as natural language processing, machine learning, and artificial intelligence. Commercial applications of StableLM models may include chatbots, virtual assistants, and sentiment analysis.
— — — — — — — — — — — — — — — —
Rank #2 a16z/magi
https://github.com/a16z/magi
A blazing fast OP Stack rollup client written in Rust
Language: Rust
Stars: 292(44 stars today) Forks:28
Magi is an OP Stack rollup client written in Rust that performs the same functionality as op-node. It is compatible with execution clients like op-geth and aims to enhance the safety and liveness of the entire OP Stack ecosystem. Magi is intended to be used as an independent implementation, and for critical infrastructure, using op-node is recommended. The project can be applied in the field of blockchain technology, specifically in the area of Layer 2 scaling solutions. Commercial applications of Magi may include the development of decentralized applications, smart contracts, and decentralized finance (DeFi) platforms. The project is open source and welcomes contributions from the community. However, it comes with a disclaimer that it is being provided “as is” and that users should proceed with caution and use it at their own risk.
— — — — — — — — — — — — — — — —
Rank #3 StanfordBDHG/HealthGPT
https://github.com/StanfordBDHG/HealthGPT
Query your Apple Health data with natural language 💬 🩺
Language: Swift
Stars: 769(202 stars today) Forks:62
— — — — — — — — — — — — — — — —
Rank #4 haotian-liu/LLaVA
https://github.com/haotian-liu/LLaVA
Large Language-and-Vision Assistant built towards multimodal GPT-4 level capabilities.
Language: Python
Stars: 1,009(213 stars today) Forks:52
— — — — — — — — — — — — — — — —
Rank #5 microsoft/semantic-kernel
https://github.com/microsoft/semantic-kernel
Integrate cutting-edge LLM technology quickly and easily into your apps
Language: C#
Stars: 6,090(427 stars today) Forks:614
— — — — — — — — — — — — — — — —
Rank #6 suno-ai/bark
https://github.com/suno-ai/bark
🔊 Text-Prompted Generative Audio Model
Language: Python
Stars: 2,469(1,661 stars today) Forks:130
Bark is a transformer-based text-to-audio model developed by Suno that can generate highly realistic, multilingual speech as well as other audio, including music, background noise, and simple sound effects. The model can also produce nonverbal communications like laughing, sighing, and crying. Bark can be applied in various fields, such as speech synthesis, audio production, and voice cloning. It has commercial applications in creating voice-overs for videos, audiobooks, and other media projects. Bark also has the capability to fully clone voices, including tone and inflection, which can be useful for creating personalized voice assistants or voice actors for virtual characters. Suno provides access to pretrained model checkpoints ready for inference to support the research community. Bark also supports various languages out-of-the-box and automatically determines language from input text. English quality is currently the best, and other languages are expected to further improve with scaling.
— — — — — — — — — — — — — — — —
Rank #7 xtekky/gpt4free
https://github.com/xtekky/gpt4free
decentralising the Ai Industry, free gpt-4/3.5 scripts through several reverse engineered api’s ( poe.com, phind.com, chat.openai.com etc…)
Language: Python
Stars: 779(428 stars today) Forks:78
— — — — — — — — — — — — — — — —
Rank #8 liou666/polyglot
https://github.com/liou666/polyglot
🤖️ 桌面端AI语言练习应用
Language: TypeScript
Stars: 763(142 stars today) Forks:64
— — — — — — — — — — — — — — — —
Rank #9 tsale/EDR-Telemetry
https://github.com/tsale/EDR-Telemetry
This project aims to compare and evaluate the telemetry of various EDR products.
Language: Python
Stars: 164(48 stars today) Forks:14
EDR Telemetry is a project that provides a comprehensive comparison of telemetry features from EDR products and other endpoint agents such as Sysmon broken down by category. The main objective of this project is to enable security practitioners to compare and evaluate the telemetry potential from those tools while encouraging EDR vendors to be more transparent about the telemetry features they provide to their users and customers. This project can be applied in the field of cybersecurity, specifically in threat detection, investigation, and forensics. Rich log telemetry empowers cyber defense teams to develop custom hunting, detection, and analytics capabilities tailored to their needs. The commercial applications of this project include providing a comprehensive comparison of EDR products to potential customers, which can help them make informed decisions when choosing an EDR product that suits their needs. The project also enables EDR vendors to improve their telemetry features to meet the needs of their customers. The telemetry comparison table in this project provides a detailed breakdown of the telemetry features of each product, which can help customers compare and evaluate the capabilities of different EDR products.
— — — — — — — — — — — — — — — —
Rank #10 Vision-CAIR/MiniGPT-4
https://github.com/Vision-CAIR/MiniGPT-4
MiniGPT-4: Enhancing Vision-language Understanding with Advanced Large Language Models
Language: Python
Stars: 11,898(2,652 stars today) Forks:1,183
— — — — — — — — — — — — — — — —
Rank #11 xcanwin/KeepChatGPT
https://github.com/xcanwin/KeepChatGPT
让我们在使用ChatGPT过程中更高效、更顺畅，完美解决ChatGPT网络错误，不再频繁地刷新网页，足足省去10个多余的步骤。还可以取消后台监管审计。解决了这几类报错: (1) NetworkError when attempting to fetch resource. (2) Something went wrong. If this issue persists please contact us through our help center at help.openai.com. (3) This content may violate our content policy. (4) Conversation not found.
Language: JavaScript
Stars: 2,736(1,061 stars today) Forks:121
— — — — — — — — — — — — — — — —
Rank #12 jackfrued/Python-100-Days
https://github.com/jackfrued/Python-100-Days
Python — 100天从新手到大师
Language: Python
Stars: 134,249(427 stars today) Forks:48,805
— — — — — — — — — — — — — — — —
Rank #13 ashawkey/stable-dreamfusion
https://github.com/ashawkey/stable-dreamfusion
A pytorch implementation of text-to-3D dreamfusion, powered by stable diffusion.
Language: Python
Stars: 4,869(186 stars today) Forks:430
— — — — — — — — — — — — — — — —
Rank #14 mouredev/Hello-Python
https://github.com/mouredev/Hello-Python
Curso para aprender el lenguaje de programación Python desde cero y para principiantes. Más de 30 clases, 25 horas en vídeo, código y grupo de chat. Desde sus fundamentos hasta la creación de un API Backend con base de datos y más…
Language: Python
Stars: 11,757(144 stars today) Forks:808
— — — — — — — — — — — — — — — —
Rank #15 aleskxyz/reality-ezpz
https://github.com/aleskxyz/reality-ezpz
Reality EZPZ
Language: Shell
Stars: 97(31 stars today) Forks:21
Reality-ezpz is a script that allows users to install and configure the Reality protocol on their Linux servers by executing a single command. The script installs Docker with a compose plugin, generates a docker-compose.yml, and Reality (Xray) configuration. It also generates a client configuration string and QR code. The script supports various operating systems, including Ubuntu, Debian, CentOS, and Fedora. The project can be applied in the field of cybersecurity, specifically in securing network traffic and blocking malware and adult content. The commercial applications of this project include providing a secure and private network for businesses and individuals. The project is easy to use and provides advanced configuration options, such as changing the SNI domain, transport protocol, and blocking malware and adult content. The script also supports natvps.net servers and allows users to regenerate configuration and keys or uninstall the configuration and services.
— — — — — — — — — — — — — — — —
Rank #16 h2oai/h2o-llmstudio
https://github.com/h2oai/h2o-llmstudio
H2O LLM Studio — a framework and no-code GUI for fine-tuning LLMs
Language: Python
Stars: 323(113 stars today) Forks:23
H2O LLM Studio is a framework and no-code GUI designed for fine-tuning state-of-the-art large language models (LLMs). With H2O LLM Studio, users can easily and effectively fine-tune LLMs without the need for any coding experience. The project can be applied in various fields, including natural language processing, chatbots, and language generation. The commercial applications of this project include providing businesses and individuals with a powerful tool for creating and fine-tuning language models that can be used for various purposes, such as customer support, content generation, and language translation. The framework offers a graphic user interface (GUI) specially designed for large language models, and users can fine-tune any LLM using a large variety of hyperparameters. The project also supports recent fine-tuning techniques such as Low-Rank Adaptation (LoRA) and 8-bit model training with a low memory footprint. H2O LLM Studio offers advanced evaluation metrics to judge generated answers by the model and allows users to track and compare their model performance visually. The project also offers Neptune integration, which can be used to track experiments and results. Users can easily export their model to the Hugging Face Hub and share it with the community. The project requires a machine with Ubuntu 16.04+ and at least one recent Nvidia GPU with Nvidia drivers version >= 470.57.02. The project is easy to set up, and users can start H2O LLM Studio using a command-line interface (CLI) or GUI.
— — — — — — — — — — — — — — — —
Rank #17 zilliztech/GPTCache
https://github.com/zilliztech/GPTCache
GPTCache is a library for creating semantic cache to store responses from LLM queries.
Language: Python
Stars: 1,857(196 stars today) Forks:126
— — — — — — — — — — — — — — — —
Rank #18 geekyutao/Inpaint-Anything
https://github.com/geekyutao/Inpaint-Anything
Inpaint anything using Segment Anything and inpainting models.
Language: Jupyter Notebook
Stars: 1,539(182 stars today) Forks:93
— — — — — — — — — — — — — — — —
Rank #19 OpenBMB/BMTools
https://github.com/OpenBMB/BMTools
Tool Learning for Big Models, Open-Source Solutions of ChatGPT-Plugins
Language: Python
Stars: 305(45 stars today) Forks:26
BMTools is an open-source repository that extends language models using tools and serves as a platform for the community to build and share tools. The project is inspired by the open-source project LangChain and optimized for the usage of open-sourced tools like ChatGPT-Plugins, striving to achieve the open-source academic version of ChatGPT-Plugins. The project can be applied in various fields, including natural language processing, chatbots, and language generation. The commercial applications of this project include providing businesses and individuals with a powerful tool for creating and fine-tuning language models that can be used for various purposes, such as customer support, content generation, and language translation. In this repository, users can easily build a plugin by writing Python functions and use external ChatGPT-Plugins. The project also supports local and online tools and allows users to use a single tool or multiple tools at the same time. The project offers a web demo that allows users to add their plugins to the mappings and start the web demo. The current version of BMTools is far from perfect, and the project will continue to improve.
— — — — — — — — — — — — — — — —
Rank #20 opendilab/awesome-RLHF
https://github.com/opendilab/awesome-RLHF
A curated list of reinforcement learning with human feedback resources (continually updated)
Language:
Stars: Star(105 stars today) Forks:41
The Awesome RLHF (RL with Human Feedback) project is a collection of research papers and codebases focused on Reinforcement Learning with Human Feedback (RLHF). RLHF involves using methods from reinforcement learning to optimize a language model with human feedback, aligning it to complex human values. The project seeks to address the challenges of RL in scenarios where the agent has limited access to feedback from the environment and requires human input to improve its performance. RLHF is an active research area in artificial intelligence, with applications in fields such as robotics, gaming, and personalized recommendation systems. The project includes advanced techniques such as Inverse Reinforcement Learning (IRL), Apprenticeship Learning, Interactive Machine Learning (IML), and Human-in-the-Loop Reinforcement Learning (HITLRL), which have been developed to improve the performance of RLHF systems. This project is a valuable resource for researchers and practitioners interested in RLHF and its applications.
— — — — — — — — — — — — — — — —
Rank #21 EwingYangs/awesome-open-gpt
https://github.com/EwingYangs/awesome-open-gpt
Collection of Open Source Projects Related to GPT，GPT相关开源项目合集🚀、精选🔥🔥
Language: Python
Stars: 1,479(101 stars today) Forks:139
— — — — — — — — — — — — — — — —
Rank #22 cuynu/ytvanced
https://github.com/cuynu/ytvanced
YouTube Vanced & Vanced MicroG & YouTube Music Vanced Unofficial (non-profit)
Language: Kotlin
Stars: 2,444(70 stars today) Forks:182
YouTube Vanced is an unofficial project, based on ReVanced patches, maintained by Cuynu. This project is temporarily discontinued, but it has been downloaded a significant number of times. The project offers a modified version of the YouTube app that includes additional features, such as ad-blocking, background playback, and themes. The modified app is available in different versions, including non-root variants, and can be downloaded for different Android architectures. The project is not associated with Team Vanced and is developed by a single person. As an unofficial project, users should be cautious about the possibility of malware, backdoors, or keyloggers. YouTube Vanced has commercial applications for users who want to enjoy an ad-free YouTube experience or want to use YouTube in the background while using other apps. However, users should be aware of the potential risks of using an unofficial app and should take appropriate measures to protect their devices.
— — — — — — — — — — — — — — — —
Rank #23 type-challenges/type-challenges
https://github.com/type-challenges/type-challenges
Collection of TypeScript type challenges with online judge
Language: TypeScript
Stars: 32,652(110 stars today) Forks:3,404
The Collection of TypeScript type challenges is a project aimed at helping developers better understand how TypeScript’s type system works by providing a collection of challenges. These challenges are designed to test and improve developers’ skills in writing high-quality types that can help improve projects’ maintainability while avoiding potential bugs. The challenges are organized by tags and difficulty levels, ranging from warm-up challenges to hard challenges. The project also includes links to several awesome type utility libraries, such as ts-toolbelt and utility-types, which can help developers in their work with types. The project can be applied in various fields that use TypeScript, including web development, mobile app development, and desktop app development. Commercial applications of this project include the development of high-quality software with fewer bugs and better maintainability, which can lead to increased customer satisfaction and reduced development costs.
— — — — — — — — — — — — — — — —
Rank #24 pyscript/pyscript
https://github.com/pyscript/pyscript
Home Page: https://pyscript.net Examples: https://pyscript.net/examples
Language: Python
Stars: 15,905(32 stars today) Forks:1,226
PyScript is a framework that allows users to create rich Python applications in the browser using HTML’s interface and the power of Pyodide, WASM, and modern web technologies. It is a meta-project that combines multiple open technologies into a framework that allows users to create sophisticated browser applications with Python. PyScript integrates seamlessly with the way the DOM works in the browser and allows users to add Python logic in a way that feels natural to both web and Python developers. The framework includes a REPL component that is rendered to the page as a code editor and allows users to write executable code. PyScript has been tested only on Chrome at the moment and is an experimental project, so users should expect things to break. PyScript has commercial applications in web development, where it can be used to create sophisticated browser applications with Python, improving the user experience and providing a more intuitive interface. It can also be used in data science and machine learning applications, where Python is a popular language for data analysis and modeling.
— — — — — — — — — — — — — — — —
Rank #25 muellerberndt/micro-gpt
https://github.com/muellerberndt/micro-gpt
A minimal generic autonomous agent based on GPT-3.5 / GPT-4. Can analyze stock prices, perform network security tests, create art, and order pizza.
Language: Python
Stars: 1,556(282 stars today) Forks:138
— — — — — — — — — — — — — — — —
