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…

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

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

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

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

Start building LLM-empowered multi-agent applications in an easier way.

[NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models

PyTorch implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and ....

Context aware, pluggable and customizable data protection and de-identification SDK for text and images

fastNLP: A Modularized and Extensible NLP Framework. Currently still in incubation.

An autoregressive character-level language model for making more things

Open weights LLM from Google DeepMind.

higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.

ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.

OpenICL is an open-source framework to facilitate research, development, and prototyping of in-context learning.

Unofficial Python API for character.ai

Generalized and Efficient Blackbox Optimization System

An easy way to host your own AI API and expose alternative models, while being compatible with "open" AI clients.

📝 Automatically annotate papers using LLMs

ICML'2022: Black-Box Tuning for Language-Model-as-a-Service & EMNLP'2022: BBTv2: Towards a Gradient-Free Future with Large Language Models

Code and Data for Tau-Bench

Code and written solutions of the assignments of the Stanford CS224N: Natural Language Processing with Deep Learning course from winter 2022/2023

TAP: An automated jailbreaking method for black-box LLMs

👤 Multi-Armed Bandit Algorithms Library (MAB) 👮

Python Meta-Feature Extractor package.

Tree of Attacks (TAP) Jailbreaking Implementation

On Transferability of Prompt Tuning for Natural Language Processing