--- title: "happy-llm vs start-llms" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/datawhalechina-happy-llm-vs-louisfb01-start-llms" tools: ["datawhalechina-happy-llm", "louisfb01-start-llms"] --- # happy-llm vs start-llms *GraphCanon updated Sep 20, 2026* ## Verdict Pick happy-llm if happy-LLM is a comprehensive tutorial for learning about large language models, focusing on NLP basics, Transformer architecture, and practical implementation of LLaMA2; pick start-llms if a comprehensive beginner-friendly guide oriented towards developing Large Language Model (LLM) skills through the latest methods and industry practices. [happy-llm](https://datawhalechina.github.io/happy-llm/) reports 34k GitHub stars, 3.2k forks, and 70 open issues, last pushed Aug 8, 2026. [start-llms](https://www.louisbouchard.ai/from-zero-to-hero-with-llms/) has 982 stars, 128 forks, and 3 open issues, last pushed Jan 23, 2026. Figures are from public GitHub metadata via [happy-llm's repository](https://github.com/datawhalechina/happy-llm) and [start-llms's repository](https://github.com/louisfb01/start-llms). | | [happy-llm](/tools/datawhalechina-happy-llm.md) | [start-llms](/tools/louisfb01-start-llms.md) | | --- | --- | --- | | Tagline | 从零开始构建大模型 | A comprehensive guide for beginners to advance in LLM skills and stay current with industry developments. | | Stars | 33,889 | 982 | | Forks | 3,210 | 128 | | Open issues | 70 | 3 | | Language | Jupyter Notebook | - | | Adopt for | Happy-LLM is a comprehensive tutorial for learning about large language models, focusing on NLP basics, Transformer architecture, and practical implementation of LLaMA2. | A comprehensive beginner-friendly guide oriented towards developing Large Language Model (LLM) skills through the latest methods and industry practices. | | Persona | - | - | | Runtime | - | - | | License | The license is not specified as open source, but the content is free to use and learn from. | MIT | | Categories | Developer Tools, LLM Frameworks, Model Training | Evaluation & Observability, Model Training | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [happy-llm](/tools/datawhalechina-happy-llm.md) | [start-llms](/tools/louisfb01-start-llms.md) | | --- | --- | --- | | Maintenance | Steady (60%) | Slowing (36%) | | Days since push | 40d | 238d | | Open issues (now) | 70 | 3 | | Stars delta | +902 (30d) | +3 (30d) | | Open issues delta | +6 (30d) | +1 (30d) | | Owner type | Organization | User | | Full report | [trust report](/tools/datawhalechina-happy-llm/trust.md) | [trust report](/tools/louisfb01-start-llms/trust.md) | ## Decision facts: happy-llm - **Requirements:** Min 8 GB RAM; Hardware recommendations and setup instructions are provided in the '学习与环境准备' section. - **Adopt for:** Happy-LLM is a comprehensive tutorial for learning about large language models, focusing on NLP basics, Transformer architecture, and practical implementation of LLaMA2. - **License detail:** The license is not specified as open source, but the content is free to use and learn from. ## Decision facts: start-llms - **Adopt for:** A comprehensive beginner-friendly guide oriented towards developing Large Language Model (LLM) skills through the latest methods and industry practices. ## Choose when ### Choose happy-llm if… - License: happy-llm is Other, start-llms is MIT. - Requirements: Min 8 GB RAM; Hardware recommendations and setup instructions are provided in the '学习与环境准备' section.. - Tags unique to happy-llm: agent, llm. - Also covers Developer Tools, LLM Frameworks. - When you need a detailed guide to understand the principles and training process of large language models, especially if you are interested in hands-on implementation of LLaMA2. ### Choose start-llms if… - License: start-llms is MIT, happy-llm is Other. - Tags unique to start-llms: ai, fine-tuning, gpt, language-model. - Also covers Evaluation & Observability. - You are a newcomer to LLMs looking for an accessible introductory pathway. ## When NOT to use happy-llm - If you are seeking a tool for immediate deployment of large language models without the need for understanding the underlying principles. - When you require a resource that focuses solely on the latest research papers and cutting-edge algorithms without a systematic learning path. - If you prefer English-language resources, as the primary content is in Chinese, although an English version is available. ## When NOT to use start-llms - You already have advanced expertise or are a seasoned professional who prefers to dive deep into specialized areas immediately. - Your primary objective is real-time collaboration features for model development teams, as the repository does not highlight these aspects. ## Common questions ### What is the difference between happy-llm and start-llms? happy-llm: 从零开始构建大模型. start-llms: A comprehensive guide for beginners to advance in LLM skills and stay current with industry developments.. See the comparison table for live GitHub stats and shared categories. ### When should I choose happy-llm over start-llms? Choose happy-llm over start-llms when License: happy-llm is Other, start-llms is MIT; Requirements: Min 8 GB RAM; Hardware recommendations and setup instructions are provided in the '学习与环境准备' section.; Tags unique to happy-llm: agent, llm; Also covers Developer Tools, LLM Frameworks; When you need a detailed guide to understand the principles and training process of large language models, especially if you are interested in hands-on implementation of LLaMA2. ### When should I choose start-llms over happy-llm? Choose start-llms over happy-llm when License: start-llms is MIT, happy-llm is Other; Tags unique to start-llms: ai, fine-tuning, gpt, language-model; Also covers Evaluation & Observability; You are a newcomer to LLMs looking for an accessible introductory pathway. ### When should I avoid happy-llm? If you are seeking a tool for immediate deployment of large language models without the need for understanding the underlying principles. When you require a resource that focuses solely on the latest research papers and cutting-edge algorithms without a systematic learning path. If you prefer English-language resources, as the primary content is in Chinese, although an English version is available. ### When should I avoid start-llms? You already have advanced expertise or are a seasoned professional who prefers to dive deep into specialized areas immediately. Your primary objective is real-time collaboration features for model development teams, as the repository does not highlight these aspects. ### Is happy-llm or start-llms more popular on GitHub? happy-llm has more GitHub stars (33,889 vs 982). Stars measure visibility, not whether either tool fits your constraints. ### Are happy-llm and start-llms open source? Yes - both are open-source projects on GitHub (happy-llm: Other, start-llms: MIT). ### Where can I find alternatives to happy-llm or start-llms? GraphCanon lists graph-backed alternatives at [happy-llm alternatives](/tools/datawhalechina-happy-llm/alternatives) and [start-llms alternatives](/tools/louisfb01-start-llms/alternatives) ([happy-llm markdown twin](/tools/datawhalechina-happy-llm/alternatives.md), [start-llms markdown twin](/tools/louisfb01-start-llms/alternatives.md)), ranked by typed relationship edges rather than popularity votes. ### Is there a machine-readable version of this comparison? Yes. The markdown twin at [this comparison](/compare/datawhalechina-happy-llm-vs-louisfb01-start-llms.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, happy-llm or start-llms? happy-llm: Steady. start-llms: Slowing. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance. ### Where are the full trust reports for happy-llm and start-llms? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [happy-llm trust report](/tools/datawhalechina-happy-llm/trust); [start-llms trust report](/tools/louisfb01-start-llms/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=datawhalechina-happy-llm`](/api/graphcanon/graph?tool=datawhalechina-happy-llm) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_