An open-source AI agent that brings the power of Gemini directly into your terminal.

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

This benchmark tests how well LLMs incorporate a set of 10 mandatory story elements (characters, objects, core concepts, attributes, motivations, etc.) in a short creative story

Puzzles for learning Triton

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

LLM training in simple, raw C/CUDA

REST: Retrieval-Based Speculative Decoding, NAACL 2024

A collection of AWESOME things about mixture-of-experts

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

maximal update parametrization (µP)

Rime Squirrel 鼠须管配置文件（朙月拼音、小鹤双拼、自然码双拼）

Easily create large video dataset from video urls

A high-throughput and memory-efficient inference and serving engine for LLMs

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文全文总结+专业翻译+润色+审稿+审稿回复

[ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.

A guidance language for controlling large language models.

ImageBind One Embedding Space to Bind Them All

A markup-based typesetting system that is powerful and easy to learn.

Official github repo for C-Eval, a Chinese evaluation suite for foundation models [NeurIPS 2023]

Tool Learning for Big Models, Open-Source Solutions of ChatGPT-Plugins

A playbook for systematically maximizing the performance of deep learning models.

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

StableLM: Stability AI Language Models

LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath

BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

A hyper-fast local vector database for use with LLM Agents. Now accepting SAFEs at $135M cap.

⚡LLM Zoo is a project that provides data, models, and evaluation benchmark for large language models.⚡

MNBVC(Massive Never-ending BT Vast Chinese corpus)超大规模中文语料集。对标chatGPT训练的40T数据。MNBVC数据集不但包括主流文化，也包括各个小众文化甚至火星文的数据。MNBVC数据集包括新闻、作文、小说、书籍、杂志、论文、台词、帖子、wiki、古诗、歌词、商品介绍、笑话、糗事、聊天记录等一切形式的纯文本中文数据。

Train transformer language models with reinforcement learning.