Peft Fine Tuning
v0.1.0Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
⭐ 1· 2k·5 current·5 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the content: SKILL.md and references contain recipes for LoRA/QLoRA, adapter management, memory optimizations, and related tooling (transformers, peft, bitsandbytes). Required artifacts (model downloads, pip-installed packages) align with fine-tuning LLMs.
Instruction Scope
Instructions are focused on fine-tuning and troubleshooting. They instruct network activity (pip install, huggingface model downloads, cloning bitsandbytes), building bitsandbytes from source, and running conversion scripts — all expected for the domain but worth noting because they cause code download and local compilation which execute on the host.
Install Mechanism
No install spec in the skill bundle (instruction-only). The runtime guidance uses pip and GitHub, which is normal for Python ML workflows; nothing in the bundle performs arbitrary downloads itself.
Credentials
The skill declares no required environment variables, credentials, or config paths. The instructions may implicitly need access to network, disk, and GPU, which are proportionate to model download/training tasks.
Persistence & Privilege
Skill is instruction-only, always:false, and does not request persistent privileges or to modify other skills or agent configurations.
Assessment
This is a how-to guide for PEFT-style fine-tuning; it appears internally consistent. Before you run it: (1) be prepared for large network downloads (LLM weights can be many GB) and local disk use; (2) pip installing packages and building bitsandbytes from source will run code on your machine—only run these commands on trusted systems and inspect commands if you have concerns; (3) some models (e.g., meta-llama variants) may require explicit licensing or HuggingFace authentication—this skill does not request credentials but you may need them to access certain models; (4) follow GPU/CUDA compatibility notes in troubleshooting to avoid runtime failures. If you want to be extra cautious, run package installs in an isolated virtual environment or container and verify any third-party scripts (e.g., convert-hf-to-gguf.py or cloned build scripts) before executing them.Like a lobster shell, security has layers — review code before you run it.
latestvk9787xem1w36zcv8nz7b0qkh2x7zyd2h
License
MIT-0
Free to use, modify, and redistribute. No attribution required.