Junhua LU (akiori)

akiori

Geek Repo

Company:Zhejiang University

Location:Hangzhou, Zhejiang, P.R.China

Home Page:akiori.github.io

Github PK Tool:Github PK Tool

Junhua LU's starred repositories

llama

Inference code for Llama models

Language:PythonLicense:NOASSERTIONStargazers:56461Issues:526Issues:992

open-interpreter

A natural language interface for computers

Language:PythonLicense:AGPL-3.0Stargazers:55529Issues:416Issues:972

leetcode-master

《代码随想录》LeetCode 刷题攻略:200道经典题目刷题顺序,共60w字的详细图解,视频难点剖析,50余张思维导图,支持C++,Java,Python,Go,JavaScript等多语言版本,从此算法学习不再迷茫!🔥🔥 来看看,你会发现相见恨晚!🚀

LLaMA-Factory

Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

Language:PythonLicense:Apache-2.0Stargazers:34554Issues:213Issues:5292

autogen

A programming framework for agentic AI 🤖

Language:PythonLicense:CC-BY-4.0Stargazers:34419Issues:400Issues:1944

HanLP

中文分词 词性标注 命名实体识别 依存句法分析 成分句法分析 语义依存分析 语义角色标注 指代消解 风格转换 语义相似度 新词发现 关键词短语提取 自动摘要 文本分类聚类 拼音简繁转换 自然语言处理

Language:PythonLicense:Apache-2.0Stargazers:33934Issues:1139Issues:1411

LLMs-from-scratch

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Language:Jupyter NotebookLicense:NOASSERTIONStargazers:33090Issues:358Issues:104

chinese-programmer-wrong-pronunciation

**程序员容易发音错误的单词

llama-recipes

Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama for WhatsApp & Messenger.

Language:Jupyter NotebookLicense:NOASSERTIONStargazers:15223Issues:193Issues:379

Qwen

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

Language:PythonLicense:Apache-2.0Stargazers:14197Issues:104Issues:1053

pytorch-deep-learning

Materials for the Learn PyTorch for Deep Learning: Zero to Mastery course.

Language:Jupyter NotebookLicense:MITStargazers:11068Issues:113Issues:206

python-mastery

Advanced Python Mastery (course by @dabeaz)

Language:PythonLicense:CC-BY-SA-4.0Stargazers:10707Issues:83Issues:36

practical-python

Practical Python Programming (course by @dabeaz)

Language:PythonLicense:CC-BY-SA-4.0Stargazers:9912Issues:343Issues:81

facechain

FaceChain is a deep-learning toolchain for generating your Digital-Twin.

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:9118Issues:88Issues:345

XAgent

An Autonomous LLM Agent for Complex Task Solving

Language:PythonLicense:Apache-2.0Stargazers:8167Issues:75Issues:306

UFO

A UI-Focused Agent for Windows OS Interaction.

Language:PythonLicense:MITStargazers:7921Issues:709Issues:22

ms-swift

Use PEFT or Full-parameter to finetune 400+ LLMs or 100+ MLLMs. (LLM: Qwen2.5, Llama3.2, GLM4, Internlm2.5, Yi1.5, Mistral, Baichuan2, DeepSeek, Gemma2, ...; MLLM: Qwen2-VL, Qwen2-Audio, Llama3.2-Vision, Llava, InternVL2, MiniCPM-V-2.6, GLM4v, Xcomposer2.5, Yi-VL, DeepSeek-VL, Phi3.5-Vision, ...)

Language:PythonLicense:Apache-2.0Stargazers:4286Issues:23Issues:1314

Rath

Next generation of automated data exploratory analysis and visualization platform.

Language:TypeScriptLicense:AGPL-3.0Stargazers:4274Issues:47Issues:144

Chinese-Vicuna

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

Language:CLicense:Apache-2.0Stargazers:4144Issues:58Issues:245

ChatGLM-Efficient-Tuning

Fine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调

Language:PythonLicense:Apache-2.0Stargazers:3671Issues:32Issues:374

tailchat

Next generation noIM application in your own workspace, not only another Slack/Discord/Rocket.chat

Language:TypeScriptLicense:Apache-2.0Stargazers:2932Issues:23Issues:228

ChatGLM-Finetuning

基于ChatGLM-6B、ChatGLM2-6B、ChatGLM3-6B模型,进行下游具体任务微调,涉及Freeze、Lora、P-tuning、全参微调等

LLMTest_NeedleInAHaystack

Doing simple retrieval from LLM models at various context lengths to measure accuracy

Language:Jupyter NotebookLicense:NOASSERTIONStargazers:1565Issues:17Issues:26

lm-format-enforcer

Enforce the output format (JSON Schema, Regex etc) of a language model

Language:PythonLicense:MITStargazers:1544Issues:13Issues:115

PasteMe

PasteMe 是一个无需注册的文本分享平台(未登陆状态下只能使用阅后即焚),可以为文本设置密码和阅后即焚,支持二维码分享和各种一键复制,针对代码提供了额外的高亮功能。

VisCPM

[ICLR'24 spotlight] Chinese and English Multimodal Large Model Series (Chat and Paint) | 基于CPM基础模型的中英双语多模态大模型系列

Knowledge-QA-LLM

QA based on local knowledge and LLM.

Language:PythonLicense:Apache-2.0Stargazers:193Issues:7Issues:10

LLMs-Interview-Prep-Guide

Welcome to the LLMs Interview Prep Guide! This GitHub repository offers a curated set of interview questions and answers tailored for Data Scientists. Enhance your understanding of Large Language Models, prepare for technical interviews, and excel in the evolving landscape of data science with a focus on LLM applications.

License:GPL-3.0Stargazers:98Issues:2Issues:0