koalazf99

llama.cpp

LLM inference in C/C++

open-interpreter

A natural language interface for computers

gkd

基于无障碍，高级选择器，订阅规则的自定义屏幕点击 Android 应用 | An Android APP with custom screen tapping based on Accessibility, Advanced Selectors, and Subscription Rules

pyautogui

A cross-platform GUI automation Python module for human beings. Used to programmatically control the mouse & keyboard.

Megatron-LM

Ongoing research training transformer models at scale

self-operating-computer

A framework to enable multimodal models to operate a computer.

AppAgent

AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.

alignment-handbook

Robust recipes to align language models with human and AI preferences

OpenAgents

[COLM 2024] OpenAgents: An Open Platform for Language Agents in the Wild

weak-to-strong

SWE-bench

[ICLR 2024] SWE-Bench: Can Language Models Resolve Real-world Github Issues?

DeepSeek-LLM

DeepSeek LLM: Let there be answers

megablocks

open-instruct

evalplus

Rigourous evaluation of LLM-synthesized code - NeurIPS 2023

LookaheadDecoding

llm-hallucination-survey

Reading list of hallucination in LLMs. Check out our new survey paper: "Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models"

MergeLM

Codebase for Merging Language Models (ICML 2024)

Lemur

[ICLR 2024] Lemur: Open Foundation Models for Language Agents

LLM-Shearing

[ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

lumos

Code and data for "Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs"

deita

Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]

MathVista

MathVista: data, code, and evaluation for Mathematical Reasoning in Visual Contexts

git-theta

git extension for {collaborative, communal, continual} model development

auto-j

Generative Judge for Evaluating Alignment

gemini-benchmark

iclr2024-openreview-submissions

ICLR 2024 OpenReivew Submission Data

WorldModelPapers

Paper collections of the continuous effort start from World Models.

text2reward

[ICLR 2024] Code for the paper "Text2Reward: Automated Dense Reward Function Generation for Reinforcement Learning"

ConvRe

🤖ConvRe🤯: An Investigation of LLMs’ Inefficacy in Understanding Converse Relations (EMNLP 2023)