njucsxh (cdhx)

cdhx

Geek Repo

Company:Nanjing University

Location:Nanjing, Jiangsu Province, China

Home Page:https://cdhx.github.io/

Github PK Tool:Github PK Tool

njucsxh's starred repositories

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:32780Issues:204Issues:5044

vllm

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

Language:PythonLicense:Apache-2.0Stargazers:28856Issues:243Issues:4926

paper-reading

深度学习经典、新论文逐段精读

License:Apache-2.0Stargazers:26762Issues:727Issues:0

unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Language:PythonLicense:MITStargazers:19938Issues:306Issues:1366

graphrag

A modular graph-based Retrieval-Augmented Generation (RAG) system

Language:PythonLicense:MITStargazers:18264Issues:116Issues:481

llama3-from-scratch

llama3 implementation one matrix multiplication at a time

Language:Jupyter NotebookLicense:MITStargazers:13589Issues:93Issues:16

academicpages.github.io

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

Language:JavaScriptLicense:MITStargazers:12146Issues:91Issues:366

open_clip

An open source implementation of CLIP.

Language:PythonLicense:NOASSERTIONStargazers:10086Issues:78Issues:483

trl

Train transformer language models with reinforcement learning.

Language:PythonLicense:Apache-2.0Stargazers:9806Issues:74Issues:1172

WizardLM

LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath

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 NotebookLicense:Apache-2.0Stargazers:8513Issues:65Issues:158

Qwen2

Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.

ragas

Supercharge Your LLM Application Evaluations 🚀

Language:PythonLicense:Apache-2.0Stargazers:6966Issues:36Issues:824

BlackFriday-GPTs-Prompts

List of free GPTs that doesn't require plus subscription

llm_interview_note

主要记录大语言大模型(LLMs) 算法(应用)工程师相关的知识及面试题

OS-Copilot

An self-improving embodied conversational agent seamlessly integrated into the operating system to automate our daily tasks.

Language:PythonLicense:MITStargazers:1484Issues:21Issues:29

LLM-Agents-Papers

A repo lists papers related to LLM based agent

Awesome-DeepLearning-500FAQ

深度学习500问,以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述,以帮助自己及有需要的读者。 全书分为18个章节,50余万字。声明:所有内容来自(仅供学习):https://github.com/scutan90/DeepLearning-500-questions

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:413Issues:9Issues:1

personal_chatgpt

personal chatgpt

Language:Jupyter NotebookStargazers:306Issues:6Issues:0

deepLearning_Interview100questions

七月在线学习整理-深度学习面试100题

WorldModelPapers

Paper collections of the continuous effort start from World Models.

License:MITStargazers:129Issues:10Issues:0

tau-bench

Code and Data for Tau-Bench

Language:PythonLicense:MITStargazers:112Issues:8Issues:3

awesome-auto-alignment

Collection of papers for scalable automated alignment.

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:31Issues:2Issues:2

SysBench

SysBench: Can Large Language Models Follow System Messages?

LLM-Alignment

A Survey of LLM Alignment (SFT & RLHF), and A Survey of RLHF methods

MarkQA

Code and data for EMNLP 2023 research track paper "MarkQA: A large scale KBQA dataset with numerical reasoning"

Language:PythonStargazers:10Issues:2Issues:0