---
title: "LLM-Adapters vs P-tuning-v2"
type: "comparison"
canonical_url: "https://www.graphcanon.com/compare/agi-edgerunners-llm-adapters-vs-thudm-p-tuning-v2"
tools: ["agi-edgerunners-llm-adapters", "thudm-p-tuning-v2"]
---

# LLM-Adapters vs P-tuning-v2

*GraphCanon updated Sep 26, 2026*

## Verdict

Pick LLM-Adapters if lLM-Adapters offers Python-based tools for efficient fine-tuning of language models with Apache-2.0 licensing; pick P-tuning-v2 if p-tuning-v2 is an optimized deep prompt tuning strategy that can be used for tasks like natural language processing and parameter-efficient learning where few parameters need to be adjusted compared to full fine-tuning.

[LLM-Adapters](https://arxiv.org/abs/2304.01933) reports 1.2k GitHub stars, 116 forks, and 55 open issues, last pushed Mar 10, 2024. [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 [LLM-Adapters's repository](https://github.com/AGI-Edgerunners/LLM-Adapters) and [P-tuning-v2's repository](https://github.com/THUDM/P-tuning-v2).

| | [LLM-Adapters](/tools/agi-edgerunners-llm-adapters.md) | [P-tuning-v2](/tools/thudm-p-tuning-v2.md) |
| --- | --- | --- |
| Tagline | Code for EMNLP 2023 Paper on Parameter-Efficient Fine-Tuning of LLMs | Optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks |
| Stars | 1,235 | 2,080 |
| Forks | 116 | 212 |
| Open issues | 55 | 35 |
| Language | Python | Python |
| Adopt for | LLM-Adapters offers Python-based tools for efficient fine-tuning of language models with Apache-2.0 licensing. | P-tuning-v2 is an optimized deep prompt tuning strategy that can be used for tasks like natural language processing and parameter-efficient learning where few parameters need to be adjusted compared to full fine-tuning. |
| Persona | - | - |
| Runtime | - | - |
| License | Apache-2.0 | P-tuning-v2 is provided under the Apache-2.0 license which permits free use, modification and distribution as long as copyright and license notice are preserved. |
| Categories | LLM Frameworks, Model Training | Model Training |

## Trust and health

_Sourced signals - not a safety guarantee. No winner column._

| | [LLM-Adapters](/tools/agi-edgerunners-llm-adapters.md) | [P-tuning-v2](/tools/thudm-p-tuning-v2.md) |
| --- | --- | --- |
| Days since push | 923d | 1045d |
| Open issues (now) | 55 | 35 |
| Stars delta | +1 (30d) | +3 (30d) |
| Full report | [trust report](/tools/agi-edgerunners-llm-adapters/trust.md) | [trust report](/tools/thudm-p-tuning-v2/trust.md) |

## Shared compatibility

- **Python**: [LLM-Adapters](/tools/agi-edgerunners-llm-adapters.md) - Python runtime; [P-tuning-v2](/tools/thudm-p-tuning-v2.md) - Python runtime

## Decision facts: LLM-Adapters

- **Adopt for:** LLM-Adapters offers Python-based tools for efficient fine-tuning of language models with Apache-2.0 licensing.

## Decision facts: P-tuning-v2

- **Requirements:** Min 8 GB RAM; Experiments were conducted on NVIDIA DGX-A100; however, RTX 3090 or RTX 2080 Ti GPUs can suffice given certain conditions.; CUDA version should be at least 11.1 and specific versions of pytorch (1.7.1), torchvision (0.8.2) and torchaudio (0.7.2).; A conda environment setup with Python 3.8.5 is recommended for optimal performance.
- **Adopt for:** P-tuning-v2 is an optimized deep prompt tuning strategy that can be used for tasks like natural language processing and parameter-efficient learning where few parameters need to be adjusted compared to full fine-tuning.
- **License detail:** P-tuning-v2 is provided under the Apache-2.0 license which permits free use, modification and distribution as long as copyright and license notice are preserved.

## Choose when

### Choose LLM-Adapters if…

- Tags unique to LLM-Adapters: adapters, fine-tuning, large-language-models, parameter-efficient.
- Also covers LLM Frameworks.
- Optimizing resource usage when you need to fine-tune large language models without altering their core parameters

### Choose P-tuning-v2 if…

- Requirements: Min 8 GB RAM; Experiments were conducted on NVIDIA DGX-A100; however, RTX 3090 or RTX 2080 Ti GPUs can suffice given certain conditions.; CUDA version should be at least 11.1 and specific versions of pytorch (1.7.1), torchvision (0.8.2) and torchaudio (0.7.2).; A conda environment setup with Python 3.8.5 is recommended for optimal performance..
- Tags unique to P-tuning-v2: natural language processing, p-tuning, parameter-efficient-learning, pretrained-language-model.
- For scenarios requiring efficient use of resources, as P-tuning v2 requires fewer parameters than traditional fine-tuning methods.

## When NOT to use LLM-Adapters

- You require a full retraining approach that modifies all model weights, not just adapters
- Your project timeline does not allow for integrating and testing new methodologies from recent papers like EMNLP 2023

## When NOT to use P-tuning-v2

- Avoid using P-tuning v2 when you have large-scale datasets and model architectures, as it might not be as effective compared to full fine-tuning methods.
- If your project requires a high level of customization beyond prompt tuning or continuous prompts do not align with the problem complexity.

## Common questions

### What is the difference between LLM-Adapters and P-tuning-v2?

LLM-Adapters: Code for EMNLP 2023 Paper on Parameter-Efficient Fine-Tuning of LLMs. P-tuning-v2: 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 LLM-Adapters over P-tuning-v2?

Choose LLM-Adapters over P-tuning-v2 when Tags unique to LLM-Adapters: adapters, fine-tuning, large-language-models, parameter-efficient; Also covers LLM Frameworks; Optimizing resource usage when you need to fine-tune large language models without altering their core parameters.

### When should I choose P-tuning-v2 over LLM-Adapters?

Choose P-tuning-v2 over LLM-Adapters when Requirements: Min 8 GB RAM; Experiments were conducted on NVIDIA DGX-A100; however, RTX 3090 or RTX 2080 Ti GPUs can suffice given certain conditions.; CUDA version should be at least 11.1 and specific versions of pytorch (1.7.1), torchvision (0.8.2) and torchaudio (0.7.2).; A conda environment setup with Python 3.8.5 is recommended for optimal performance.; Tags unique to P-tuning-v2: natural language processing, p-tuning, parameter-efficient-learning, pretrained-language-model; For scenarios requiring efficient use of resources, as P-tuning v2 requires fewer parameters than traditional fine-tuning methods.

### When should I avoid LLM-Adapters?

You require a full retraining approach that modifies all model weights, not just adapters Your project timeline does not allow for integrating and testing new methodologies from recent papers like EMNLP 2023

### When should I avoid P-tuning-v2?

Avoid using P-tuning v2 when you have large-scale datasets and model architectures, as it might not be as effective compared to full fine-tuning methods. If your project requires a high level of customization beyond prompt tuning or continuous prompts do not align with the problem complexity.

### Is LLM-Adapters or P-tuning-v2 more popular on GitHub?

P-tuning-v2 has more GitHub stars (2,080 vs 1,235). Stars measure visibility, not whether either tool fits your constraints.

### Are LLM-Adapters and P-tuning-v2 open source?

Yes - both are open-source projects on GitHub (LLM-Adapters: Apache-2.0, P-tuning-v2: Apache-2.0).

### Where can I find alternatives to LLM-Adapters or P-tuning-v2?

GraphCanon lists graph-backed alternatives at [LLM-Adapters alternatives](/tools/agi-edgerunners-llm-adapters/alternatives) and [P-tuning-v2 alternatives](/tools/thudm-p-tuning-v2/alternatives) ([LLM-Adapters markdown twin](/tools/agi-edgerunners-llm-adapters/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/agi-edgerunners-llm-adapters-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, LLM-Adapters or P-tuning-v2?

LLM-Adapters: Dormant. 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 LLM-Adapters and P-tuning-v2?

GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [LLM-Adapters trust report](/tools/agi-edgerunners-llm-adapters/trust); [P-tuning-v2 trust report](/tools/thudm-p-tuning-v2/trust).

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon/graph?tool=agi-edgerunners-llm-adapters`](/api/graphcanon/graph?tool=agi-edgerunners-llm-adapters)
- 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/_