--- title: "LLMs-from-scratch vs KnowledgeEditingPapers" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/rasbt-llms-from-scratch-vs-zjunlp-knowledgeeditingpapers" tools: ["rasbt-llms-from-scratch", "zjunlp-knowledgeeditingpapers"] --- # LLMs-from-scratch vs KnowledgeEditingPapers *GraphCanon updated Jul 12, 2026* ## Verdict Pick LLMs-from-scratch if lLMs-from-scratch is a project-oriented repository aimed at building PyTorch-based language models from the ground up, with detailed step-by-step instructions; pick KnowledgeEditingPapers if a specialized collection of foundational papers and reports that delve into the editing and manipulation of knowledge within large language models, making it a valuable resource for researchers looking to understand and斧. [LLMs-from-scratch](https://amzn.to/4fqvn0D) reports 99k GitHub stars, 15k forks, and 4 open issues, last pushed Jun 2, 2026. [KnowledgeEditingPapers](https://github.com/zjunlp/KnowledgeEditingPapers) has 1.2k stars, 79 forks, and 0 open issues, last pushed Jun 25, 2026. Figures are from public GitHub metadata via [LLMs-from-scratch's repository](https://github.com/rasbt/LLMs-from-scratch) and [KnowledgeEditingPapers's repository](https://github.com/zjunlp/KnowledgeEditingPapers). | | [LLMs-from-scratch](/tools/rasbt-llms-from-scratch.md) | [KnowledgeEditingPapers](/tools/zjunlp-knowledgeeditingpapers.md) | | --- | --- | --- | | Tagline | Implement a ChatGPT-like LLM in PyTorch from scratch, step by step | Must-read Papers on Knowledge Editing for Large Language Models | | Stars | 98,899 | 1,235 | | Forks | 15,183 | 79 | | Open issues | 4 | 0 | | Language | Jupyter Notebook | - | | Adopt for | LLMs-from-scratch is a project-oriented repository aimed at building PyTorch-based language models from the ground up, with detailed step-by-step instructions. | A specialized collection of foundational papers and reports that delve into the editing and manipulation of knowledge within large language models, making it a valuable resource for researchers looking to understand and斧 | | Persona | - | - | | Runtime | - | - | | License | Other | MIT | | Categories | LLM Frameworks, Model Training | LLM Frameworks, Model Training | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [LLMs-from-scratch](/tools/rasbt-llms-from-scratch.md) | [KnowledgeEditingPapers](/tools/zjunlp-knowledgeeditingpapers.md) | | --- | --- | --- | | Maintenance | Steady (60%) | Active (82%) | | Days since push | 38d | 16d | | Open issues (now) | 4 | 0 | | Owner type | User | Organization | | Full report | [trust report](/tools/rasbt-llms-from-scratch/trust.md) | [trust report](/tools/zjunlp-knowledgeeditingpapers/trust.md) | ## Decision facts: LLMs-from-scratch - **Adopt for:** LLMs-from-scratch is a project-oriented repository aimed at building PyTorch-based language models from the ground up, with detailed step-by-step instructions. ## Decision facts: KnowledgeEditingPapers - **Hosting:** unknown - **Adopt for:** A specialized collection of foundational papers and reports that delve into the editing and manipulation of knowledge within large language models, making it a valuable resource for researchers looking to understand and斧 - **License detail:** MIT ## Choose when ### Choose LLMs-from-scratch if… - License: LLMs-from-scratch is Other, KnowledgeEditingPapers is MIT. - Tags unique to LLMs-from-scratch: ai, artificial-intelligence, attention mechanism, deep-learning. - - You are an advanced practitioner aiming to fully understand the underpinnings of LLMs using PyTorch as your primary framework. ### Choose KnowledgeEditingPapers if… - License: KnowledgeEditingPapers is MIT, LLMs-from-scratch is Other. - Tags unique to KnowledgeEditingPapers: knowledge-editing, large-language-models, model-editing, natural-language-processing. - You are specifically interested in recent advancements in knowledge editing techniques for large language models. ## When NOT to use LLMs-from-scratch - - If you are looking for a rapid deployment of an LLM without understanding its intricate structure - this tool requires extensive manual and conceptual work. - - You prefer frameworks with automatic model generation or other high-level abstractions that simplify the process. This repository emphasizes manual creation, which is more time-consuming but offers丰 - a deeper learning experience. ## When NOT to use KnowledgeEditingPapers - You are looking for a broad overview of machine learning or AI in general, as this repository focuses narrowly on knowledge editing within large language models. - If you seek practical tooling or implementation guidance rather than theoretical insights and review papers. - Your focus is more on data preprocessing or model training techniques unrelated to the specific modification of knowledge mechanisms in LLMs. ## Common questions ### What is the difference between LLMs-from-scratch and KnowledgeEditingPapers? LLMs-from-scratch: Implement a ChatGPT-like LLM in PyTorch from scratch, step by step. KnowledgeEditingPapers: Must-read Papers on Knowledge Editing for Large Language Models. See the comparison table for live GitHub stats and shared categories. ### When should I choose LLMs-from-scratch over KnowledgeEditingPapers? Choose LLMs-from-scratch over KnowledgeEditingPapers when License: LLMs-from-scratch is Other, KnowledgeEditingPapers is MIT; Tags unique to LLMs-from-scratch: ai, artificial-intelligence, attention mechanism, deep-learning; - You are an advanced practitioner aiming to fully understand the underpinnings of LLMs using PyTorch as your primary framework. ### When should I choose KnowledgeEditingPapers over LLMs-from-scratch? Choose KnowledgeEditingPapers over LLMs-from-scratch when License: KnowledgeEditingPapers is MIT, LLMs-from-scratch is Other; Tags unique to KnowledgeEditingPapers: knowledge-editing, large-language-models, model-editing, natural-language-processing; You are specifically interested in recent advancements in knowledge editing techniques for large language models. ### When should I avoid LLMs-from-scratch? - If you are looking for a rapid deployment of an LLM without understanding its intricate structure - this tool requires extensive manual and conceptual work. - You prefer frameworks with automatic model generation or other high-level abstractions that simplify the process. This repository emphasizes manual creation, which is more time-consuming but offers丰 a deeper learning experience. ### When should I avoid KnowledgeEditingPapers? You are looking for a broad overview of machine learning or AI in general, as this repository focuses narrowly on knowledge editing within large language models. If you seek practical tooling or implementation guidance rather than theoretical insights and review papers. Your focus is more on data preprocessing or model training techniques unrelated to the specific modification of knowledge mechanisms in LLMs. ### Is LLMs-from-scratch or KnowledgeEditingPapers more popular on GitHub? LLMs-from-scratch has more GitHub stars (98,899 vs 1,235). Stars measure visibility, not whether either tool fits your constraints. ### Are LLMs-from-scratch and KnowledgeEditingPapers open source? Yes - both are open-source projects on GitHub (LLMs-from-scratch: Other, KnowledgeEditingPapers: MIT). ### Where can I find alternatives to LLMs-from-scratch or KnowledgeEditingPapers? GraphCanon lists graph-backed alternatives at [LLMs-from-scratch alternatives](/tools/rasbt-llms-from-scratch/alternatives) and [KnowledgeEditingPapers alternatives](/tools/zjunlp-knowledgeeditingpapers/alternatives) ([LLMs-from-scratch markdown twin](/tools/rasbt-llms-from-scratch/alternatives.md), [KnowledgeEditingPapers markdown twin](/tools/zjunlp-knowledgeeditingpapers/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/rasbt-llms-from-scratch-vs-zjunlp-knowledgeeditingpapers.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, LLMs-from-scratch or KnowledgeEditingPapers? LLMs-from-scratch: Steady. KnowledgeEditingPapers: Active. 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 LLMs-from-scratch and KnowledgeEditingPapers? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [LLMs-from-scratch trust report](/tools/rasbt-llms-from-scratch/trust); [KnowledgeEditingPapers trust report](/tools/zjunlp-knowledgeeditingpapers/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=rasbt-llms-from-scratch`](/api/graphcanon/graph?tool=rasbt-llms-from-scratch) - 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/_