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

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

A modular graph-based Retrieval-Augmented Generation (RAG) system

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

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

SkyPilot: Run AI and batch jobs on any infra (Kubernetes or 12+ clouds). Get unified execution, cost savings, and high GPU availability via a simple interface.

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

Kolors Team

Mobile-Agent: The Powerful Mobile Device Operation Assistant Family

4 bits quantization of LLaMA using GPTQ

A repo lists papers related to LLM based agent

RL research on Android devices.

DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models

A Massively Parallel Large Scale Self-Play Framework

🌍 Repository for "AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agent", ACL'24 Best Resource Paper.

LlamaTouch: A Faithful and Scalable Testbed for Mobile UI Task Automation

An environment for mobile angets to interact with realistic android device or android emulator

Implementation of LlamaTouch Evaluator