LLaMA 相关的热门 GitHub AI项目仓库

LLM inference in C/C++

ggml-org

Inference code for Llama models

meta-llama

The official Meta Llama 3 GitHub site

meta-llama

Distribute and run LLMs with a single file.

Mozilla-Ocho

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

HqWu-HITCS

Instruct-tune LLaMA on consumer hardware

tloen

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

ymcui

Inference Llama 2 in one file of pure C

karpathy

llama3 implementation one matrix multiplication at a time

naklecha

Llama中文社区，实时汇总最新Llama学习资料，构建最好的中文Llama大模型开源生态，完全开源可商用

LlamaFamily

The simplest way to run LLaMA on your local machine

cocktailpeanut

Easy-to-use and powerful LLM and SLM library with awesome model zoo.

PaddlePaddle

A command-line productivity tool powered by AI large language models like GPT-4, will help you accomplish your tasks faster and more efficiently.

TheR1D

Python bindings for llama.cpp

abetlen

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

jzhang38

High-speed Large Language Model Serving for Local Deployment

SJTU-IPADS

BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

LianjiaTech

Composable building blocks to build Llama Apps

meta-llama

OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset

openlm-research

Java version of LangChain

langchain4j

中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models)

ymcui

Utilities intended for use with Llama models.

meta-llama

Giving Kubernetes Superpowers to everyone

k8sgpt-ai

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

InternLM

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.

Lightning-AI

🎉 Repo for LaWGPT, Chinese-Llama tuned with Chinese Legal knowledge. 基于中文法律知识的大语言模型

pengxiao-song

[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

OpenGVLab

AirLLM 70B inference with single 4GB GPU

lyogavin

A web interface for chatting with Alpaca through llama.cpp. Fully dockerized, with an easy to use API.

serge-chat

A large-scale 7B pretraining language model developed by BaiChuan-Inc.

baichuan-inc

Tools for merging pretrained large language models.

arcee-ai

A self-organizing file system with llama 3

iyaja

Build a Perplexity-Inspired Answer Engine Using Next.js, Groq, Llama-3, Langchain, OpenAI, Upstash, Brave & Serper

developersdigest

YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open

multimodal-art-projection

Turn any webpage into structured data using LLMs

mishushakov

Repo for BenTsao [original name: HuaTuo (华驼)], Instruction-tuning Large Language Models with Chinese Medical Knowledge. 本草（原名：华驼）模型仓库，基于中文医学知识的大语言模型指令微调

SCIR-HI

Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷

modelscope

Instruction Tuning with GPT-4

Instruction-Tuning-with-GPT-4

Agentic components of the Llama Stack APIs

meta-llama

g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains

bklieger-groq

High-speed download of LLaMA, Facebook's 65B parameter GPT model

shawwn

Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案，结构参考alpaca

Facico

Llama3、Llama3.1 中文后训练版仓库（微调、魔改版本有趣权重 & 训练、推理、评测、部署教程视频 & 文档）

CrazyBoyM

Knowledge Agents and Management in the Cloud

run-llama

MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO、GRPO。

shibing624

TensorZero creates a feedback loop for optimizing LLM applications — turning production data into smarter, faster, and cheaper models.

tensorzero

A library of data loaders for LLMs made by the community -- to be used with LlamaIndex and/or LangChain

run-llama

中文nlp解决方案(大模型、数据、模型、训练、推理)

yuanzhoulvpi2017

Fault-tolerant, highly scalable GPU orchestration, and a machine learning framework designed for training models with billions to trillions of parameters

higgsfield-ai

雅意大模型：为客户打造安全可靠的专属大模型，基于大规模中英文多领域指令数据训练的 LlaMA 2 & BLOOM 系列模型，由中科闻歌算法团队研发。(Repo for YaYi Chinese LLMs based on LlaMA2 & BLOOM)

wenge-research

基于LangChain和ChatGLM-6B等系列LLM的针对本地知识库的自动问答

X-D-Lab

InternGPT (iGPT) is an open source demo platform where you can easily showcase your AI models. Now it supports DragGAN, ChatGPT, ImageBind, multimodal chat like GPT-4, SAM, interactive image editing, etc. Try it at igpt.opengvlab.com (支持DragGAN、ChatGPT、ImageBind、SAM的在线Demo系统)

OpenGVLab

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

ModelTC

A C#/.NET library to run LLM (🦙LLaMA/LLaVA) on your local device efficiently.

SciSharp

Set of tools to assess and improve LLM security.

meta-llama

4 bits quantization of LLaMA using GPTQ

qwopqwop200

Chinese-LLaMA 1&2、Chinese-Falcon 基础模型；ChatFlow中文对话模型；中文OpenLLaMA模型；NLP预训练/指令微调数据集

CVI-SZU

[EMNLP 2023 Demo] Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding

DAMO-NLP-SG

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

predibase

LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.

ictnlp