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.
npx skills add librefang/librefang-registry --skill llm-finetuninggit clone --depth 1 https://github.com/librefang/librefang-registryWrote 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.
[](https://agentmods.dev/skills/librefang/librefang-registry/llm-finetuning)<a href="https://agentmods.dev/skills/librefang/librefang-registry/llm-finetuning"><img src="https://agentmods.dev/badge/skills/librefang/librefang-registry/llm-finetuning/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00026 | $0.00831 |
| Opus 5.5 | $0.00010 | $0.00332 |
| Sonnet 5.5 | $0.00005 | $0.00166 |
| Haiku 4.5 | $0.00003 | $0.00083 |
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 1mo 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.
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.
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
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.
- 1mo ago First seen · 42 lines · 26 tokens per session scan A 2b9ac5a1c60a
llm-finetuning is a skill published in the GitHub repository librefang/librefang-registry (11 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 831 once invoked, about $0.0001 per session on Opus 5.5. 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.
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…
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…
torch-geometric
Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.
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.
glycobiology
Glycosylation site prediction and glycobiology analysis. N-glycosylation motif finding, O-glycosylation hotspot prediction, glycan structure resources. Lightweight, pure Python. For protein function queries use uniprot-database; for structure analysis use alphafold-database.
pyhealth
Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC)…