A platform for developers to simulate research community

OpenAI 接口接入适配，支持千帆大模型平台、讯飞星火大模型、腾讯混元以及MiniMax、Deep-Seek，等兼容OpenAI接口，仅单可执行文件，配置超级简单，一键部署，开箱即用. Seamlessly integrate with OpenAI and compatible APIs using a single executable for quick setup and depl…

A modular high-level library to train embodied AI agents across a variety of tasks and environments.

Free ChatGPT API Key，免费ChatGPT API，支持GPT4 API（免费），ChatGPT国内可用免费转发API，直连无需代理。可以搭配ChatBox等软件/插件使用，极大降低接口使用成本。国内即可无限制畅快聊天。

An open-source RAG-based tool for chatting with your documents.

Robust recipes to align language models with human and AI preferences

The hub for EleutherAI's work on interpretability and learning dynamics

This is the official implementation for our ACL 2024 paper: "Causal Estimation of Memorisation Profiles".

Things you can do with the token embeddings of an LLM

High-performance retrieval engine for unstructured data

BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)

A python module to repair invalid JSON, commonly used to parse the output of LLMs

A collection of handy Bash One-Liners and terminal tricks for data processing and Linux system maintenance.

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

A simple pip-installable Python tool to generate your own HTML citation world map from your Google Scholar ID.

Agentic components of the Llama Stack APIs

✨ A framework-agnostic tool that converts any layout into a drag-to-swap one with just a few lines of code https://swapy.tahazsh.com/

Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"

The Memory layer for your AI apps

Industrial-first evaluation benchmark for LLMs in the DevOps/AIOps domain.

An Open-source Framework for Data-centric, Self-evolving Autonomous Language Agents

An open-source framework for collaborative AI agents, enabling diverse, distributed agents to team up and tackle complex tasks through internet-like connectivity.

LLM training in simple, raw C/CUDA

Together Mixture-Of-Agents (MoA) – 65.1% on AlpacaEval with OSS models

MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.

An Awesome List to LLM Instruction Following

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

Inspect: A framework for large language model evaluations

A Toolkit for Running On-device Large Language Models (LLMs) in APP