iszhuangsha

iszhuangsha's Stars

• modelscope/swift

  ms-swift: Use PEFT or Full-parameter to finetune 250+ LLMs or 40+ MLLMs. (Qwen2, GLM4, Internlm2, Yi, Llama3, Llava, MiniCPM-V, Deepseek, Baichuan2, Gemma2, Phi3-Vision, ...)

  Language:Python2.2k212

• EvolvingLMMs-Lab/lmms-eval

  Accelerating the development of large multimodal models (LMMs) with lmms-eval

  Language:Python1k54

• TinyLLaVA/TinyLLaVA_Factory

  A Framework of Small-scale Large Multimodal Models

  Language:Python47439

• haotian-liu/LLaVA

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

  Language:Python17.9k1.9k

• datawhalechina/so-large-lm

  大模型基础: 一文了解大模型基础知识

  1.8k165

• LLM-Testing/LLM4SoftwareTesting

  18111

• run-llama/finetune-embedding

  Fine-Tuning Embedding for RAG with Synthetic Data

  Language:Jupyter Notebook43160

• codefuse-ai/Awesome-Code-LLM

  A curated list of language modeling researches for code and related datasets.

  1k71

• karpathy/nanoGPT

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

  Language:Python34.4k5.3k

• charent/Phi2-mini-Chinese

  Phi2-Chinese-0.2B 从0开始训练自己的Phi2中文小模型，支持接入langchain加载本地知识库做检索增强生成RAG。Training your own Phi2 small chat model from scratch.

  Language:Jupyter Notebook42246

• DLLXW/baby-llama2-chinese

  用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.

  Language:Python2.3k283

• jiahe7ay/MINI_LLM

  This is a repository used by individuals to experiment and reproduce the pre-training process of LLM.

  Language:Python27045

• shibing624/MedicalGPT

  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。

  Language:Python2.9k450

• hiyouga/LLaMA-Factory

  Unify Efficient Fine-Tuning of 100+ LLMs

  Language:Python25.5k3.2k

• bigcode-project/starcoder2

  Home of StarCoder2!

  Language:Python1.6k151

• mzbac/llama2-fine-tune

  Scripts for fine-tuning Llama2 via SFT and DPO.

  Language:Python16236

• datawhalechina/self-llm

  《开源大模型食用指南》基于Linux环境快速部署开源大模型，更适合**宝宝的部署教程

  Language:Jupyter Notebook6k741

• liguodongiot/llm-action

  本项目旨在分享大模型相关技术原理以及实战经验。

  Language:HTML7.5k739

• wp931120/text2sql

  prompt engineering ，llm，text2sql

  Language:Python272

• jayli/langchain-GLM_Agent

  本地知识库 + chatGLM6B + CustomAgent

  Language:Python23747

• datawhalechina/llm-cookbook

  面向开发者的 LLM 入门教程，吴恩达大模型系列课程中文版

  Language:Jupyter Notebook10.4k1.2k

• datawhalechina/llm-universe

  本项目是一个面向小白开发者的大模型应用开发教程，在线阅读地址：https://datawhalechina.github.io/llm-universe/

  Language:Jupyter Notebook3.4k450

• MorvanZhou/Reinforcement-learning-with-tensorflow

  Simple Reinforcement learning tutorials, 莫烦Python 中文AI教学

  Language:Python8.7k5k

• liaokongVFX/LangChain-Chinese-Getting-Started-Guide

  LangChain 的中文入门教程

  7.1k567

• Goooaaal/Oh_My_Bot_and_My_QA

  基于Seq2Seq的多轮对话系统和基于LSTM的问答机制

  Language:Python319

• xiaobaicxy/STM_Multi_Turn_Responses_Selcetion_Pytorch

  Pytorch实现STM（Spatio-Temporal Matching network）多轮对话算法

  Language:Python6

• datawhalechina/leedl-tutorial

  《李宏毅深度学习教程》（李宏毅老师推荐👍），PDF下载地址：https://github.com/datawhalechina/leedl-tutorial/releases

  Language:Jupyter Notebook10.9k2.6k

• datawhalechina/hugging-llm

  HuggingLLM, Hugging Future.

  Language:Jupyter Notebook2.6k338

• MLNLP-World/Awesome-LLM

  This project collects awesome resources (e.g., papers, open-source models) for large language model (LLM)

  24022

• Lizhi-sjtu/DRL-code-pytorch

  Concise pytorch implements of DRL algorithms, including REINFORCE, A2C, DQN, PPO(discrete and continuous), DDPG, TD3, SAC.

  Language:Python947162