--- title: "surogate vs LLMs-from-scratch" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/invergent-ai-surogate-vs-rasbt-llms-from-scratch" tools: ["invergent-ai-surogate", "rasbt-llms-from-scratch"] --- # surogate vs LLMs-from-scratch *GraphCanon updated Jul 11, 2026* ## Verdict Pick surogate when surogate is primarily C++; LLMs-from-scratch is Jupyter Notebook; pick LLMs-from-scratch when lLMs-from-scratch is primarily Jupyter Notebook; surogate is C++. [surogate](https://surogate.ai) reports 806 GitHub stars, 6 forks, and 7 open issues, last pushed Jul 7, 2026. [LLMs-from-scratch](https://amzn.to/4fqvn0D) has 99k stars, 15k forks, and 4 open issues, last pushed Jun 2, 2026. Figures are from public GitHub metadata via [surogate's repository](https://github.com/invergent-ai/surogate) and [LLMs-from-scratch's repository](https://github.com/rasbt/LLMs-from-scratch). | | [surogate](/tools/invergent-ai-surogate.md) | [LLMs-from-scratch](/tools/rasbt-llms-from-scratch.md) | | --- | --- | --- | | Tagline | Training/Fine-tuning at the speed of light | Implement a ChatGPT-like LLM in PyTorch from scratch, step by step | | Stars | 806 | 98,899 | | Forks | 6 | 15,183 | | Open issues | 7 | 4 | | Language | C++ | 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. | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | Other | | Categories | LLM Frameworks, Model Training | LLM Frameworks, Model Training | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [surogate](/tools/invergent-ai-surogate.md) | [LLMs-from-scratch](/tools/rasbt-llms-from-scratch.md) | | --- | --- | --- | | Maintenance | Very active (96%) | Steady (60%) | | Days since push | 4d | 38d | | Open issues (now) | 7 | 4 | | Owner type | Organization | User | | Full report | [trust report](/tools/invergent-ai-surogate/trust.md) | [trust report](/tools/rasbt-llms-from-scratch/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. ## Choose when ### Choose surogate if… - surogate is primarily C++; LLMs-from-scratch is Jupyter Notebook. - License: surogate is Apache-2.0, LLMs-from-scratch is Other. - Tags unique to surogate: cuda, fine-tuning, llama, llm. ### Choose LLMs-from-scratch if… - LLMs-from-scratch is primarily Jupyter Notebook; surogate is C++. - License: LLMs-from-scratch is Other, surogate is Apache-2.0. - Tags unique to LLMs-from-scratch: ai, artificial-intelligence, attention mechanism, finetuning. - - You are an advanced practitioner aiming to fully understand the underpinnings of LLMs using PyTorch as your primary framework. ## When NOT to use surogate - LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. - Model Training: Try prompting and RAG first; fine-tuning is the answer to style/format, not missing knowledge. ## 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. ## Common questions ### What is the difference between surogate and LLMs-from-scratch? surogate: Training/Fine-tuning at the speed of light. LLMs-from-scratch: Implement a ChatGPT-like LLM in PyTorch from scratch, step by step. See the comparison table for live GitHub stats and shared categories. ### When should I choose surogate over LLMs-from-scratch? Choose surogate over LLMs-from-scratch when surogate is primarily C++; LLMs-from-scratch is Jupyter Notebook; License: surogate is Apache-2.0, LLMs-from-scratch is Other; Tags unique to surogate: cuda, fine-tuning, llama, llm. ### When should I choose LLMs-from-scratch over surogate? Choose LLMs-from-scratch over surogate when LLMs-from-scratch is primarily Jupyter Notebook; surogate is C++; License: LLMs-from-scratch is Other, surogate is Apache-2.0; Tags unique to LLMs-from-scratch: ai, artificial-intelligence, attention mechanism, finetuning; - You are an advanced practitioner aiming to fully understand the underpinnings of LLMs using PyTorch as your primary framework. ### When should I avoid surogate? LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. Model Training: Try prompting and RAG first; fine-tuning is the answer to style/format, not missing knowledge. ### 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. ### Is surogate or LLMs-from-scratch more popular on GitHub? LLMs-from-scratch has more GitHub stars (98,899 vs 806). Stars measure visibility, not whether either tool fits your constraints. ### Are surogate and LLMs-from-scratch open source? Yes - both are open-source projects on GitHub (surogate: Apache-2.0, LLMs-from-scratch: Other). ### Where can I find alternatives to surogate or LLMs-from-scratch? GraphCanon lists graph-backed alternatives at [surogate alternatives](/tools/invergent-ai-surogate/alternatives) and [LLMs-from-scratch alternatives](/tools/rasbt-llms-from-scratch/alternatives) ([surogate markdown twin](/tools/invergent-ai-surogate/alternatives.md), [LLMs-from-scratch markdown twin](/tools/rasbt-llms-from-scratch/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/invergent-ai-surogate-vs-rasbt-llms-from-scratch.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, surogate or LLMs-from-scratch? surogate: Very active. LLMs-from-scratch: Steady. 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 surogate and LLMs-from-scratch? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [surogate trust report](/tools/invergent-ai-surogate/trust); [LLMs-from-scratch trust report](/tools/rasbt-llms-from-scratch/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=invergent-ai-surogate`](/api/graphcanon/graph?tool=invergent-ai-surogate) - 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/_