Stars
A simple Python Pydantic model for Honkai: Star Rail parsed data from the Mihomo API.
An autoregressive character-level language model for making more things
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API
MetaStyle: Three-Way Trade-Off Among Speed, Flexibility, and Quality in Neural Style Transfer
猫抓 浏览器资源嗅探扩展 / cat-catch Browser Resource Sniffing Extension
Automated generation of planar geometry olympiad problems
An environment for learning formal mathematical reasoning from scratch
Implementation of CVPR2022 paper: Transform-Retrieve-Generate: Natural Language-Centric Outside-Knowledge Visual Question Answering
CivRealm is an interactive environment for the open-source strategy game Freeciv-web based on Freeciv, a Civilization-inspired game.
This repo contains code for our NeurIPS 2023 spotlight paper: Evaluating and Inducing Personality in Pre-trained Language Models
Streamlit — A faster way to build and share data apps.
🕹️ A diverse suite of scalable reinforcement learning environments in JAX
This repo contains code for our ICML 2023 paper: MEWL: Few-shot multimodal word learning with referential uncertainty
Integrating ChatGPT into your browser deeply, everything you need is here
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, m…
Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
Translation of the databricks-dolly-15k dataset to Chinese for commercial use.
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
Official implementation of CVPR23 paper "Diffusion-based Generation, Optimization, and Planning in 3D Scenes"
ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Official implementation of "From Zero to Hero: Convincing with Extremely Complicated Math".