Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
- artificial-intelligence
- attention-mechanisms
- deep-learning
- reinforcement-learning
100,822 visible repositories in the index
625–648 of 6,500 · Most stars
Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
cryptography is a package designed to expose cryptographic primitives and recipes to Python developers.
Translated⛽️ "Algorithm Clearance Handbook": A learning tutorial on "algorithms and data structures" starting from zero, with 200 "popular algorithm interview questions" and 1000+ "LeetCode problem analyses", continuously updated!
ODS V3 Pre-Release: Public testing and refinement ahead of the official V3 launch. Turn your PC, Mac, or Linux box into a private AI server.
A framework for efficient model inference with omni-modality models
Flexible and powerful framework for managing multiple AI agents and handling complex conversations
Open-source implementation of AlphaEvolve
Skills for threat modeling, scanning, triage, patching, plus an autonomous scanning harness you can /customize
Official Matplotlib cheat sheets
The official repository for ERNIE 4.5 and ERNIEKit – its industrial-grade development toolkit based on PaddlePaddle.
The cryptography-based networking stack for building unstoppable networks with LoRa, Packet Radio, WiFi and everything in between.
Semantic Image Synthesis with SPADE
Official Python client library for kubernetes
A supercharged Git/GitHub command line interface (CLI). An official integration for GitHub and GitHub Enterprise: https://github.com/works-with/category/desktop-tools
TranslatedSelf-hosted knowledge agent platform for RAG, knowledge graphs and multi-agent workflows. Yuxi = Cloud Agents + Knowledge RAG, Self-hosted knowledge agent platform for RAG, knowledge graphs and multi-agent workflows.
Everything about Web Application Firewalls (WAFs) from Security Standpoint! 🔥
Official Kaggle CLI
PaperBanana: Automating Academic Illustration For AI Scientists
GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)
OpenCompass is an LLM evaluation platform, supporting a wide range of models from OpenAI, Anthropic, Gemini, Qwen, GLM, DeepSeek, etc, across 100+ datasets covering knowledge, reasoning, coding, science, language, long-context, and safety.
You're reading this. The skill predicted it. A workflow that turns every post into a calibrated experiment—score, blind-predict, retro, evolve. The future doesn't reward effort, it rewards those who see the pattern first. 1M followers in a month — not luck, system.
TranslatedDamai automatic ticket grabbing, supports selection of attendees, cities, date sessions, and prices
Efficiently computes derivatives of NumPy code.
This repo powers my experiment where ChatGPT manages a real-money micro-cap stock portfolio.