--- title: "LLMs-from-scratch vs P-tuning-v2" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/rasbt-llms-from-scratch-vs-thudm-p-tuning-v2" tools: ["rasbt-llms-from-scratch", "thudm-p-tuning-v2"] --- # LLMs-from-scratch vs P-tuning-v2 *GraphCanon updated Jul 11, 2026* ## Verdict Pick LLMs-from-scratch when lLMs-from-scratch is primarily Jupyter Notebook; P-tuning-v2 is Python; pick P-tuning-v2 when p-tuning-v2 is primarily Python; LLMs-from-scratch is Jupyter Notebook. [LLMs-from-scratch](https://amzn.to/4fqvn0D) reports 99k GitHub stars, 15k forks, and 4 open issues, last pushed Jun 2, 2026. [P-tuning-v2](https://github.com/THUDM/P-tuning-v2) has 2.1k stars, 212 forks, and 35 open issues, last pushed Nov 16, 2023. Figures are from public GitHub metadata via [LLMs-from-scratch's repository](https://github.com/rasbt/LLMs-from-scratch) and [P-tuning-v2's repository](https://github.com/THUDM/P-tuning-v2). | | [LLMs-from-scratch](/tools/rasbt-llms-from-scratch.md) | [P-tuning-v2](/tools/thudm-p-tuning-v2.md) | | --- | --- | --- | | Tagline | Implement a ChatGPT-like LLM in PyTorch from scratch, step by step | An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks | | Stars | 98,899 | 2,075 | | Forks | 15,183 | 212 | | Open issues | 4 | 35 | | Language | Jupyter Notebook | Python | | 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 | Other | Apache-2.0 | | Categories | LLM Frameworks, Model Training | LLM Frameworks, Model Training, Vector Databases | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [LLMs-from-scratch](/tools/rasbt-llms-from-scratch.md) | [P-tuning-v2](/tools/thudm-p-tuning-v2.md) | | --- | --- | --- | | Maintenance | Steady (60%) | Dormant (18%) | | Days since push | 38d | 968d | | Open issues (now) | 4 | 35 | | Owner type | User | Organization | | Security scan | No lockfile | 50 low (50 low) | | Full report | [trust report](/tools/rasbt-llms-from-scratch/trust.md) | [trust report](/tools/thudm-p-tuning-v2/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 LLMs-from-scratch if… - LLMs-from-scratch is primarily Jupyter Notebook; P-tuning-v2 is Python. - License: LLMs-from-scratch is Other, P-tuning-v2 is Apache-2.0. - Tags unique to LLMs-from-scratch: deep-learning, ai, artificial-intelligence, attention-mechanism. - - You are an advanced practitioner aiming to fully understand the underpinnings of LLMs using PyTorch as your primary framework. ### Choose P-tuning-v2 if… - P-tuning-v2 is primarily Python; LLMs-from-scratch is Jupyter Notebook. - License: P-tuning-v2 is Apache-2.0, LLMs-from-scratch is Other. - Tags unique to P-tuning-v2: p-tuning, python, prompt-tuning, parameter-efficient-learning. - Also covers Vector Databases. ## 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 P-tuning-v2 - Last GitHub push was 969 days ago (dormant maintenance, Nov 16, 2023). Validate activity before betting a new project on P-tuning-v2. - 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. - Vector Databases: Don't reach for a dedicated vector DB under ~100k vectors; pgvector on your existing Postgres is simpler to operate. ## Common questions ### What is the difference between LLMs-from-scratch and P-tuning-v2? LLMs-from-scratch: Implement a ChatGPT-like LLM in PyTorch from scratch, step by step. P-tuning-v2: An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks. See the comparison table for live GitHub stats and shared categories. ### When should I choose LLMs-from-scratch over P-tuning-v2? Choose LLMs-from-scratch over P-tuning-v2 when LLMs-from-scratch is primarily Jupyter Notebook; P-tuning-v2 is Python; License: LLMs-from-scratch is Other, P-tuning-v2 is Apache-2.0; Tags unique to LLMs-from-scratch: deep-learning, ai, artificial-intelligence, attention-mechanism; - You are an advanced practitioner aiming to fully understand the underpinnings of LLMs using PyTorch as your primary framework. ### When should I choose P-tuning-v2 over LLMs-from-scratch? Choose P-tuning-v2 over LLMs-from-scratch when P-tuning-v2 is primarily Python; LLMs-from-scratch is Jupyter Notebook; License: P-tuning-v2 is Apache-2.0, LLMs-from-scratch is Other; Tags unique to P-tuning-v2: p-tuning, python, prompt-tuning, parameter-efficient-learning; Also covers Vector Databases. ### 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 P-tuning-v2? Last GitHub push was 969 days ago (dormant maintenance, Nov 16, 2023). Validate activity before betting a new project on P-tuning-v2. 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. Vector Databases: Don't reach for a dedicated vector DB under ~100k vectors; pgvector on your existing Postgres is simpler to operate. ### Is LLMs-from-scratch or P-tuning-v2 more popular on GitHub? LLMs-from-scratch has more GitHub stars (98,899 vs 2,075). Stars measure visibility, not whether either tool fits your constraints. ### Are LLMs-from-scratch and P-tuning-v2 open source? Yes - both are open-source projects on GitHub (LLMs-from-scratch: Other, P-tuning-v2: Apache-2.0). ### Where can I find alternatives to LLMs-from-scratch or P-tuning-v2? GraphCanon lists graph-backed alternatives at [LLMs-from-scratch alternatives](/tools/rasbt-llms-from-scratch/alternatives) and [P-tuning-v2 alternatives](/tools/thudm-p-tuning-v2/alternatives) ([LLMs-from-scratch markdown twin](/tools/rasbt-llms-from-scratch/alternatives.md), [P-tuning-v2 markdown twin](/tools/thudm-p-tuning-v2/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-thudm-p-tuning-v2.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 P-tuning-v2? LLMs-from-scratch: Steady. P-tuning-v2: Dormant. 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 P-tuning-v2? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [LLMs-from-scratch trust report](/tools/rasbt-llms-from-scratch/trust); [P-tuning-v2 trust report](/tools/thudm-p-tuning-v2/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/_