ftgreat

llama.cpp

Port of Facebook's LLaMA model in C/C++

agentflow

Complex LLM Workflows from Simple JSON.

Anima

第一个开源的基于QLoRA的33B中文大语言模型First QLoRA based open source 33B Chinese LLM

Aquila2

The official repo of Aquila2 series proposed by BAAI, including pretrained & chat large language models.

argilla

✨Argilla: the open-source data curation platform for LLMs

awesome-llm-human-preference-datasets

A curated list of Human Preference Datasets for LLM fine-tuning, RLHF, and eval.

block-recurrent-transformer-pytorch

Implementation of Block Recurrent Transformer - Pytorch

detect-pretrain-code

This repository provides an original implementation of Detecting Pretraining Data from Large Language Models by *Weijia Shi, *Anirudh Ajith, Mengzhou Xia, Yangsibo Huang, Daogao Liu , Terra Blevins , Danqi Chen , Luke Zettlemoyer.

DISC-FinLLM

DISC-FinLLM，**金融大语言模型（LLM），旨在为用户提供金融场景下专业、智能、全面的金融咨询服务。DISC-FinLLM, a Chinese financial large language model (LLM) designed to provide users with professional, intelligent, and comprehensive financial consulting services in financial scenarios.

fairscale

PyTorch extensions for high performance and large scale training.

fastmoe

A fast MoE impl for PyTorch

ggml

Tensor library for machine learning

guidance

A guidance language for controlling large language models.

langchain

⚡ Building applications with LLMs through composability ⚡

langchain-learning

langchain学习笔记，包含langchain源码解读、langchain中使用中文模型、langchain实例等。

llama_index

LlamaIndex (GPT Index) is a data framework for your LLM applications

llm-output-parsing

LMFlow

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

local-llm-function-calling

A tool for generating function arguments and choosing what function to call with local LLMs

LongChat

Official repository for LongChat and LongEval

mistral-src

Reference implementation of Mistral AI 7B v0.1 model.

MOSS-RLHF

MOSS-RLHF

nvtop

GPUs process monitoring for AMD, Intel and NVIDIA

OpenLLaMA2

A Ray-based High-performance LLaMA2 RLHF framework

ray

Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

s4

Structured state space sequence models

text-generation-inference

Large Language Model Text Generation Inference

training-code

The code we currently use to fine-tune models.

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

vllm

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