🏆 #648 overall#205 of 2,559 in Natural Language Processing🔥 active this week

datawhalechina /diy-llm

Covers pre-training data, Tokenizer, Transformer, MoE,distributed training, Scaling Laws, inference & alignment .6 progressive code assignments for full-stack LLM learning | 涵盖预训练数据、分词器、Transformer、MoE、分布式训练、缩放定律、推理与对齐,6 项渐进代码作业,掌握 LLM 全栈知识

$ git clone https://github.com/datawhalechina/diy-llm.git
GitHub social preview for datawhalechina/diy-llm
Stars
3K
2,980
This week
+133 ★
+1.5K this month
Forks
289
289
Language
Jupyter Notebook
License
None
Created
Nov 24, 2025
1.0 years old
Last push
Nov 16, 2026
🔥 this week

Stars, last 30 days

Oct 15, 2026 → Nov 16, 2026
★ 1.5K▲ +1.5K★ 3K

Categories

GitHub topics

More in Natural Language Processing

Natural Language Processing

hiyouga/EasyR1

▲ +6 ★ this week

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

PythonApache-2.0updated Nov 8, 2026
GitHub ↗★ 5.2K⑂ 400
Natural Language Processing

tingaicompass/AI-Compass🔥 active

“AI-Compass”将为社区指引在 AI 技术海洋中航行的方向,无论你是初学者还是进阶开发者,都能在这里找到通往 AI 各大方向的路径。旨在帮助开发者系统性地了解 AI 的核心概念、主流技术、前沿趋势,并通过实践掌握从理论到落地的全过程。

Pythonno licenseupdated Nov 16, 2026
GitHub ↗★ 999⑂ 136
Natural Language Processing

tensorchord/modelz-llm

OpenAI compatible API for LLMs and embeddings (LLaMA, Vicuna, ChatGLM and many others)

PythonApache-2.0updated Oct 11, 2023
GitHub ↗★ 273⑂ 27
Natural Language Processing

telekom/create-tsi

Create-tsi is a generative AI RAG toolkit which generates AI Applications with low code.

🔍 Search & Retrieval
TypeScriptno licenseupdated Nov 4, 2024
GitHub ↗★ 233⑂ 27
Natural Language Processing

SqueezeAILab/LLM2LLM

[ACL 2024] LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement

PythonMITupdated Mar 25, 2024
GitHub ↗★ 196⑂ 15

Data from GitHub · snapshot Nov 16, 2026