diy-llm
by datawhalechina (organization)
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 (description from the project’s GitHub page)
Repository facts
- Stars
- 1,510
- Forks
- 158
- Open issues and pull requests
- 7
- Primary language
- Jupyter Notebook
- License
- No license file detected
- Owner
- datawhalechina · Organization
- Created
- Nov 24, 2025
- Last push
- Oct 9, 2026
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 513: modelscope/ms-swift
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3…
15,871 starsPythonApache-2.0Last push Oct 18, 2026
Rank 882: oumi-ai/oumi
Easily fine-tune (SFT/RL), evaluate, and deploy Qwen, Gemma, or any open agentic LLM/VLM!
9,403 starsPythonApache-2.0Last push Oct 15, 2026
Rank 5,850: JudgmentLabs/judgeval
The Continuous-Improvement Stack for Agents. Our environment data and evals power agent improvement and monitoring.
1,068 starsPythonApache-2.0Last push Oct 18, 2026
Rank 1,546: hiyouga/EasyR1
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
5,198 starsPythonApache-2.0Last push Sep 19, 2026
Rank 6,182: tingaicompass/AI-Compass
“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。
983 starsPythonNo license file detectedLast push Oct 18, 2026
Rank 14: huggingface/transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
167,814 starsPythonApache-2.0Last push Oct 18, 2026