Source: https://seerepo.com/compare/hiyouga/LlamaFactory/vs/huggingface/peft
Markdown source: https://seerepo.com/compare/hiyouga/LlamaFactory/vs/huggingface/peft.md
Description: LlamaFactory and peft share 9 technologies: Gradio, torchvision, transformers, torch, datasets, accelerate, peft, safetensors, and bitsandbytes. Both are written in Python.

# LlamaFactory vs peft

LlamaFactory and peft share 9 technologies: Gradio, torchvision, transformers, torch, datasets, accelerate, peft, safetensors, and bitsandbytes. Both are written in Python.

- [hiyouga/LlamaFactory](https://seerepo.com/r/hiyouga/LlamaFactory): Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
- [huggingface/peft](https://seerepo.com/r/huggingface/peft): 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

## What they share and what sets them apart

- In common: Gradio, torchvision, transformers, torch, datasets, accelerate, peft, safetensors, bitsandbytes
- Only in LlamaFactory: FastAPI, uvicorn, matplotlib, einops, sentencepiece, tiktoken, triton-ascend, trl, deepspeed, liger-kernel, ModelScope, torchaudio, nltk, torchdata, torchcodec, av, jsonschema-specifications, referencing, Pydantic
- Only in peft: Hugging Face, diffusers, pillow, psutil

## Side by side

| | LlamaFactory | peft |
|---|---|---|
| Size | 62,624 lines written, 194 code files | 166,024 lines written, 272 code files |
| Who writes it | 1.6% of its commits signed by AI. With Gemini CLI, Claude Code, GitHub Copilot, and Cursor | 0.1% of its commits signed by AI. With Cursor and Claude Code |
| Activity | Last push November 4, 2026, 2,769 commits, 75,890 stars | Last push November 4, 2026, 1,934 commits, 21,873 stars |
| Tests | 62 test files. 38.1% of its code files have a test that imports them | 75 test files. 0.7% of its code files have a test that imports them |

- Size: Lines written by people and agents, without generated ones; code files, without tests.
- Who writes it: A commit counts as AI's when it carries its signature: a Co-Authored-By line, its author name or the merge of its branch.
- Activity: From GitHub and its history, on the day SeeRepo read it.
- Tests: The files that test the code, and the share of code files a test imports.

## Frequently asked questions

### Which is bigger, LlamaFactory or peft?

peft, with 166,024 lines written; LlamaFactory has 62,624.

The proof: [huggingface/peft's code at commit 574c7ca](https://github.com/huggingface/peft/tree/574c7cab277827d7383ae53a0e93e22cf816f476)

### Which has more GitHub stars, LlamaFactory or peft?

LlamaFactory, with 75,890 stars; peft has 21,873.

The proof: [hiyouga/LlamaFactory on GitHub](https://github.com/hiyouga/LlamaFactory)

### Which has more tests, LlamaFactory or peft?

peft, with 75 test files; LlamaFactory has 62.

The proof: [huggingface/peft's code at commit 574c7ca](https://github.com/huggingface/peft/tree/574c7cab277827d7383ae53a0e93e22cf816f476)

### Which was updated more recently, LlamaFactory or peft?

Both got their last push on November 4, 2026.

The proof: [huggingface/peft's commits on GitHub](https://github.com/huggingface/peft/commits)

### Which has more commits signed by AI, LlamaFactory or peft?

LlamaFactory: an AI signed 1.6% of its commits, with Gemini CLI, Claude Code, GitHub Copilot, and Cursor; in peft, 0.1%.

The proof: [the commits each tool signed in hiyouga/LlamaFactory](https://seerepo.com/r/hiyouga/LlamaFactory/ai)

## Sources

- hiyouga/LlamaFactory: Read on November 4, 2026, at commit 702005c (https://github.com/hiyouga/LlamaFactory/tree/702005ce5237ae10f3c572c3f7741ecfd1422fc9)
- huggingface/peft: Read on November 5, 2026, at commit 574c7ca (https://github.com/huggingface/peft/tree/574c7cab277827d7383ae53a0e93e22cf816f476)

## What is your repo built with?

Any public repo, with no account: https://seerepo.com/r/owner/repo/built, with the owner and name it has on GitHub.