datawhalechina/base-llm
从 NLP 到 LLM 的算法全栈教程，在线阅读地址：https://datawhalechina.github.io/base-llm/
This project provides a comprehensive learning path from traditional Natural Language Processing (NLP) techniques to advanced Large Language Models (LLMs). It takes you from understanding foundational concepts like word vectors and RNNs to implementing Transformer architectures and Llama2, along with deployment strategies. AI algorithm engineers, researchers, and students interested in deep diving into LLM principles will find this valuable.
421 stars.
Use this if you are an AI developer looking to build a strong foundation in NLP and LLMs, moving beyond just API calls to understand the underlying architecture and implement models from scratch.
Not ideal if you are a beginner with no prior experience in Python, PyTorch, or deep learning concepts, as these are prerequisites for understanding the content.
Stars
421
Forks
39
Language
Jupyter Notebook
License
—
Category
Last pushed
Mar 11, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/datawhalechina/base-llm"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PaddlePaddle/PaddleNLP
Easy-to-use and powerful LLM and SLM library with awesome model zoo.
meta-llama/llama-cookbook
Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started...
arcee-ai/mergekit
Tools for merging pretrained large language models.
changyeyu/LLM-RL-Visualized
🌟100+ 原创 LLM / RL 原理图📚，《大模型算法》作者巨献！💥（100+ LLM/RL Algorithm Maps ）
mindspore-lab/step_into_llm
MindSpore online courses: Step into LLM