llm-finetuning

llm-finetuning is a skill for Claude Code, Codex from librefang/librefang-registry. It costs 26 tokens per session (831 once invoked), scanned A, a copy of llm-finetuning, MIT.

A guide to fine-tuning large language models, meaning adapting an existing model to a particular subject or task with example data. It covers dataset preparation, memory-saving LoRA and QLoRA methods, training choices, evaluation, and deployment.

In plain words
What is it for?
Use it to prepare training data, choose fine-tuning settings, run LoRA or QLoRA training with Hugging Face tools, evaluate results with task measures and human review, and deploy adapters.
Why use it?
It helps turn a general model into one that follows a specific format or handles a specific domain, while reducing unnecessary training cost and memory use.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/librefang/librefang-registry/llm-finetuning
Any agent
npx skills add librefang/librefang-registry --skill llm-finetuning
Clone the repo
git clone --depth 1 https://github.com/librefang/librefang-registry

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for llm-finetuning

README.md
[![agentmods](https://agentmods.dev/badge/skills/librefang/librefang-registry/llm-finetuning.svg)](https://agentmods.dev/skills/librefang/librefang-registry/llm-finetuning)
Your own site
<a href="https://agentmods.dev/skills/librefang/librefang-registry/llm-finetuning"><img src="https://agentmods.dev/badge/skills/librefang/librefang-registry/llm-finetuning.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 831 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 97% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00026 $0.00831
Opus 5 $0.00013 $0.00415
Sonnet 5 $0.00005 $0.00166
Haiku 4.5 $0.00003 $0.00083

Measured 5d ago against content hash 2b9ac5a1c60a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

llm-finetuning scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

97% identical to llm-finetuning — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/llm-finetuning/SKILL.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLM Fine-Tuning Expert

A deep learning specialist with hands-on expertise in fine-tuning large language models using parameter-efficient methods, dataset curation, and training optimization. This skill provides guidance for adapting foundation models to specific domains and tasks using LoRA, QLoRA, and the Hugging Face PEFT ecosystem, covering dataset preparation, hyperparameter selection, evaluation strategies, and adapter deployment.

Key Principles

  • Fine-tuning is about teaching a model your task format and domain knowledge, not about teaching it language; start with the strongest base model you can afford to run
  • Dataset quality matters far more than quantity; 1,000 carefully curated, diverse, high-quality examples often outperform 100,000 noisy ones
  • Use parameter-efficient fine-tuning (LoRA/QLoRA) to reduce memory requirements by orders of magnitude while achieving performance comparable to full fine-tuning
  • Evaluate with task-specific metrics and human review, not just perplexity; a model with lower perplexity may still produce worse outputs for your specific use case
  • Track every experiment with exact hyperparameters, dataset versions, and base model checkpoints so that results are reproducible and comparable

Techniques

  • Configure LoRA with appropriate rank (r=8 to 64), alpha (typically 2x rank), and target modules (q_proj, v_proj for attention, or all linear layers for broader adaptation)
  • Use QLoRA for memory-constrained setups: load the base model in 4-bit NormalFloat quantization, attach LoRA adapters in fp16/bf16, and train with paged optimizers to handle memory spikes
  • Format datasets as instruction-response pairs with consistent templates; include a system field for persona or context, an instruction field for the task, and a response field for the expected output
  • Apply the PEFT library workflow: load base model, create LoRA config, get_peft_model(), train with the Hugging Face Trainer or a custom loop, then save and load adapters independently
  • Set training hyperparameters carefully: learning rate between 1e-5 and 2e-4 with cosine schedule, 1-5 epochs (watch for overfitting), warmup ratio of 0.03-0.1, and gradient accumulation to simulate larger batch sizes
  • Evaluate with multiple signals: validation loss for overfitting detection, task-specific metrics (ROUGE for summarization, exact match for QA), and structured human evaluation on a held-out set

Read the full file on GitHub · 42 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 42 lines · 26 tokens per session scan A 2b9ac5a1c60a

Subscribe to this mod's changes

llm-finetuning is a skill published in the GitHub repository librefang/librefang-registry (11 stars, last pushed 11d ago), licensed MIT. It adds 26 tokens to every session and 831 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to llm-finetuning, differing in 3 lines, and is treated as a copy.

Related

Other skills, from other repositories

hugging-face-model-trainer

This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV…

synthetic-sciences/openscience · 131 tokens

histolab

Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.

synthetic-sciences/openscience · 62 tokens

deepchem

Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first…

synthetic-sciences/openscience · 78 tokens

shap

Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing…

synthetic-sciences/openscience · 109 tokens

torch-geometric

Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.

synthetic-sciences/openscience · 41 tokens

zarr-python

Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.

synthetic-sciences/openscience · 42 tokens