izhx

llama_index

LlamaIndex is a data framework for your LLM applications

guidance

A guidance language for controlling large language models.

langflow

⛓️ Langflow is a dynamic graph where each node is an executable unit. Its modular and interactive design fosters rapid experimentation and prototyping, pushing hard on the limits of creativity.

SuperAGI

<⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.

ivy

The Unified AI Framework

Awesome-Multimodal-Large-Language-Models

:sparkles::sparkles:Latest Advances on Multimodal Large Language Models

gorilla

Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

open-llms

📋 A list of open LLMs available for commercial use.

LLMsPracticalGuide

A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)

ImageBind

ImageBind One Embedding Space to Bind Them All

LMFlow

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

instructor

structured outputs for llms

awesome-langchain

😎 Awesome list of tools and projects with the awesome LangChain framework

GPTCache

Semantic cache for LLMs. Fully integrated with LangChain and llama_index.

Voyager

An Open-Ended Embodied Agent with Large Language Models

xTuring

Build, customize and control you own LLMs. From data pre-processing to fine-tuning, xTuring provides an easy way to personalize open-source LLMs. Join our discord community: https://discord.gg/TgHXuSJEk6

MineDojo

Building Open-Ended Embodied Agents with Internet-Scale Knowledge

finetuner

:dart: Task-oriented embedding tuning for BERT, CLIP, etc.

MeZO

[NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333

ONE-PEACE

A general representation model across vision, audio, language modalities. Paper: ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities

PandaLM

long-range-arena

Long Range Arena for Benchmarking Efficient Transformers

awesome-generative-information-retrieval

dreamGPT

Leverage hallucinations from Large Language Models (LLMs) for novelty-driven explorations.

Stable-Alignment

Multi-agent Social Simulation + Efficient, Effective, and Stable alternative of RLHF. Code for the paper "Training Socially Aligned Language Models in Simulated Human Society".

ContinualLM

An Extensible Continual Learning Framework Focused on Language Models (LMs)

ScienceWorld

ScienceWorld is a text-based virtual environment centered around accomplishing tasks from the standardized elementary science curriculum.

world-models

deep-language-networks

We view Large Language Models as stochastic language layers in a network, where the learnable parameters are the natural language prompts at each layer. We stack two such layers, feeding the output of one layer to the next. We call the stacked architecture a Deep Language Network - DLN

embeddings

Training Large-scale Text Embedding Models with 🤗 Transformers