DL
datawhalechina/diy-llm
🎓 系统性大语言模型构建课程｜🛠️ 覆盖预训练数据工程、Tokenizer、Transformer、MoE、GPU 编程 (CUDA/Triton)、分布式训练、Scaling Laws、推理优化及对齐 (SFT/RLHF/GRPO)｜🚀 6 个渐进式作业 + 代码驱动，建立 LLM 全栈认知体系
381 40 +64/wk
GitHub 🔥 Heating Up +24.9%
gpu-programming llm nlp rl sft transformer triton
Trend
6
Star & Fork Trend (20 data points)
Stars
Forks
Multi-Source Signals
Growth Velocity
datawhalechina/diy-llm has +64 stars this period . 7-day velocity: 24.9%.
Deep analysis is being generated for this repository.
Signal-backed technical analysis will be available soon.
| Metric | diy-llm | ai-powered-search | memora | embedding_studio |
|---|---|---|---|---|
| Stars | 381 | 381 | 381 | 384 |
| Forks | 40 | 104 | 44 | 5 |
| Weekly Growth | +64 | +0 | +0 | +0 |
| Language | Jupyter Notebook | Jupyter Notebook | Python | Python |
| Sources | 1 | 1 | 1 | 1 |
| License | N/A | N/A | MIT | Apache-2.0 |
Capability Radar vs ai-powered-search
diy-llm
ai-powered-search
Maintenance Activity 100
Last code push 0 days ago.
Community Engagement 52
Fork-to-star ratio: 10.5%. Active community forking and contributing.
Issue Burden 70
Issue data not yet available.
Growth Momentum 100
+64 stars this period — 16.80% growth rate.
License Clarity 30
No clear license detected — proceed with caution.
Risk scores are computed from real-time repository data. Higher scores indicate healthier metrics.