JKHenry520

ChatGLM-LangChain

ChatGLM 6B 的模型与UI，通过 LangChain 与向量匹配实现本地知识库问答，支持流式输出

qqgpt_basic

把chatgpt api的流式输出变为一句一句输出,适用于qq等聊天机器人

text-generation-inference

Large Language Model Text Generation Inference

doctran

LLM4IR-Survey

This is the repo for the survey of LLM4IR.

BlueLM

BlueLM(蓝心大模型): Open large language models developed by vivo AI Lab

evals

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

Baichuan2-Explained

Baichuan2代码的逐行解析版本，适合小白

LLMSurvey

The official GitHub page for the survey paper "A Survey of Large Language Models".

TinyLlama

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

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

wisdomInterrogatory

llm3s-conatiner

large language model training-3-stages+deployment

RetroMAE

Codebase for RetroMAE and beyond.

FlagEmbedding

Retrieval and Retrieval-augmented LLMs

PandaLM

pke_zh

pke_zh, python keyphrase extraction for chinese(zh). 中文关键词或关键句提取工具，实现了KeyBert、PositionRank、TopicRank、TextRank等算法，开箱即用。

LLM-Pretrain-FineTune

Deepspeed、LLM、Medical_Dialogue、医疗大模型、预训练、微调

Open-GPT

GPT is a belief. This project provides a code library for efficiently training Chinese GPT. This project uses the nanoGPT framework and the novel optimizer algorithm sophia.

nanoGPT

The simplest, fastest repository for training/finetuning medium-sized GPTs.

minGPT

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

transformers

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

gpt-2

Code for the paper "Language Models are Unsupervised Multitask Learners"

finetune-transformer-lm

Code and model for the paper "Improving Language Understanding by Generative Pre-Training"

gpt1

gpt1的简单复现

uniem

unified embedding model

FlagAI

FlagAI (Fast LArge-scale General AI models) is a fast, easy-to-use and extensible toolkit for large-scale model.

ChatGPT-RetrievalQA

A dataset for training/evaluating Question Answering Retrieval models on ChatGPT responses with the possibility to training/evaluating on real human responses.

simpleT5

simpleT5 is built on top of PyTorch-lightning⚡️ and Transformers🤗 that lets you quickly train your T5 models.

DeepSpeed-Chat-GPT2

基于DeepSpeed-Chat打造针对自己模型的三段式训练