--- title: "LlamaFactory vs P-tuning-v2" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/hiyouga-llamafactory-vs-thudm-p-tuning-v2" tools: ["hiyouga-llamafactory", "thudm-p-tuning-v2"] --- # LlamaFactory vs P-tuning-v2 *GraphCanon updated Jul 11, 2026* ## Verdict Pick LlamaFactory when tags unique to LlamaFactory: gemma, fine-tuning, deepseek, ai; pick P-tuning-v2 when tags unique to P-tuning-v2: p-tuning, python, prompt-tuning, parameter-efficient-learning. [LlamaFactory](https://llamafactory.readthedocs.io) reports 73k GitHub stars, 8.9k forks, and 1.1k open issues, last pushed Jul 10, 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 [LlamaFactory's repository](https://github.com/hiyouga/LlamaFactory) and [P-tuning-v2's repository](https://github.com/THUDM/P-tuning-v2). | | [LlamaFactory](/tools/hiyouga-llamafactory.md) | [P-tuning-v2](/tools/thudm-p-tuning-v2.md) | | --- | --- | --- | | Tagline | Unified Efficient Fine-Tuning of 100+ LLMs & VLMs | An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks | | Stars | 73,157 | 2,075 | | Forks | 8,937 | 212 | | Open issues | 1,067 | 35 | | Language | Python | Python | | Adopt for | LlamaFactory is a sophisticated tool for fine-tuning numerous large language models and visual language models efficiently using various methods such as LoRA, QLoRA, RLHF, and quantization. | - | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | 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._ | | [LlamaFactory](/tools/hiyouga-llamafactory.md) | [P-tuning-v2](/tools/thudm-p-tuning-v2.md) | | --- | --- | --- | | Maintenance | Very active (96%) | Dormant (18%) | | Days since push | 0d | 968d | | Open issues (now) | 1.1k | 35 | | Owner type | User | Organization | | Security scan | No lockfile | 50 low (50 low) | | Full report | [trust report](/tools/hiyouga-llamafactory/trust.md) | [trust report](/tools/thudm-p-tuning-v2/trust.md) | ## Decision facts: LlamaFactory - **Adopt for:** LlamaFactory is a sophisticated tool for fine-tuning numerous large language models and visual language models efficiently using various methods such as LoRA, QLoRA, RLHF, and quantization. ## Choose when ### Choose LlamaFactory if… - Tags unique to LlamaFactory: gemma, fine-tuning, deepseek, ai. - When you need to fine-tune over 100 different LLMs or VLMs with efficient methods like LoRA or QLoRA. - More GitHub stars (73k vs 2.1k) - visibility, not fit. ### Choose P-tuning-v2 if… - Tags unique to P-tuning-v2: p-tuning, python, prompt-tuning, parameter-efficient-learning. - Also covers Vector Databases. - Leaner open-issue backlog (35). ## When NOT to use LlamaFactory - When you are looking to fine-tune less popular or niche models that are not supported within the 100+ models covered by LlamaFactory. - If your project specifically requires custom fine-tuning methods not available in this repository, such as certain versions of PEFT (Parameter Efficient Fine-Tuning) techniques excluding LoRA and QLoa ## 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 LlamaFactory and P-tuning-v2? LlamaFactory: Unified Efficient Fine-Tuning of 100+ LLMs & VLMs. 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 LlamaFactory over P-tuning-v2? Choose LlamaFactory over P-tuning-v2 when Tags unique to LlamaFactory: gemma, fine-tuning, deepseek, ai; When you need to fine-tune over 100 different LLMs or VLMs with efficient methods like LoRA or QLoRA; More GitHub stars (73k vs 2.1k) - visibility, not fit. ### When should I choose P-tuning-v2 over LlamaFactory? Choose P-tuning-v2 over LlamaFactory when Tags unique to P-tuning-v2: p-tuning, python, prompt-tuning, parameter-efficient-learning; Also covers Vector Databases; Leaner open-issue backlog (35). ### When should I avoid LlamaFactory? When you are looking to fine-tune less popular or niche models that are not supported within the 100+ models covered by LlamaFactory. If your project specifically requires custom fine-tuning methods not available in this repository, such as certain versions of PEFT (Parameter Efficient Fine-Tuning) techniques excluding LoRA and QLoa ### 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 LlamaFactory or P-tuning-v2 more popular on GitHub? LlamaFactory has more GitHub stars (73,157 vs 2,075). Stars measure visibility, not whether either tool fits your constraints. ### Are LlamaFactory and P-tuning-v2 open source? Yes - both are open-source projects on GitHub (LlamaFactory: Apache-2.0, P-tuning-v2: Apache-2.0). ### Where can I find alternatives to LlamaFactory or P-tuning-v2? GraphCanon lists graph-backed alternatives at [LlamaFactory alternatives](/tools/hiyouga-llamafactory/alternatives) and [P-tuning-v2 alternatives](/tools/thudm-p-tuning-v2/alternatives) ([LlamaFactory markdown twin](/tools/hiyouga-llamafactory/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/hiyouga-llamafactory-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, LlamaFactory or P-tuning-v2? LlamaFactory: Very active. 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 LlamaFactory and P-tuning-v2? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [LlamaFactory trust report](/tools/hiyouga-llamafactory/trust); [P-tuning-v2 trust report](/tools/thudm-p-tuning-v2/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=hiyouga-llamafactory`](/api/graphcanon/graph?tool=hiyouga-llamafactory) - 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/_