fine-tuning-expert
Use when fine-tuning LLMs, training custom models, or adapting foundation models for specific tasks. Invoke for configuring LoRA/QLoRA adapters, preparing JSONL training datasets, setting hyperparameters for fine-tuning runs, adapter training, transfer learning, finetuning with Hugging Face PEFT, OpenAI fine-tuning, instruction tuning, RLHF, DPO, or quantizing and deploying fine-tuned models. Trigger terms include: LoRA, QLoRA, PEFT, finetuning, fine-tuning, adapter tuning, LLM training, model training, custom model.
- Installs
- 4.3K
- Last 24h
- +31
- Trending rank
- #4325
- Security
- Fail
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/jeffallan/claude-skills --skill fine-tuning-expert- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads fine-tuning-expert automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
Security audits
Independent scans of the skill's instructions and bundled files.
SKILL.md
The instructions your agent reads when the skill is triggered.
Fine-Tuning Expert
Senior ML engineer specializing in LLM fine-tuning, parameter-efficient methods, and production model optimization.
Core Workflow
- Dataset preparation — Validate and format data; run quality checks before training starts
- Checkpoint:
python validate_dataset.py --input data.jsonl— fix all errors before proceeding
- Checkpoint:
- Method selection — Choose PEFT technique based on GPU memory and task requirements
- Use LoRA for most tasks; QLoRA (4-bit) when GPU memory is constrained; full fine-tune only for small models
- Training — Configure hyperparameters, monitor loss curves, checkpoint regularly
- Checkpoint: validation loss must decrease; plateau or increase signals overfitting
- Evaluation — Benchmark against the base model; test on held-out set and edge cases
- Checkpoint: collect perplexity, task-specific metrics (BLEU/ROUGE), and latency numbers
- Deployment — Merge adapter weights, quantize, measure inference throughput before serving
Reference Guide
Load detailed guidance based on context:
| Topic | Reference | Load When |
|---|---|---|
| LoRA/PEFT | references/lora-peft.md | Parameter-efficient fine-tuning, adapters |
| Dataset Prep | references/dataset-preparation.md | Training data formatting, quality checks |
| Hyperparameters | references/hyperparameter-tuning.md | Learning rates, batch sizes, schedulers |
| Evaluation | references/evaluation-metrics.md | Benchmarking, metrics, model comparison |
| Deployment | references/deployment-optimization.md | Model merging, quantization, serving |
Minimal Working Example — LoRA Fine-Tuning with Hugging Face PEFT
from datasets import load_dataset
from transformers import AutoTokenizer, AutoModelForCausalLM, TrainingArguments
from peft import LoraConfig, get_peft_model, TaskType
from trl import SFTTrainer
import torch
# 1. Load base model and tokenizer
model_id = "meta-llama/Llama-3-8B"
tokenizer = AutoTokenizer.from_pretrained(model_id)
tokenizer.pad_token = tokenizer.eos_token
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
device_map="auto",
)
# 2. Configure LoRA adapter
lora_config = LoraConfig(
task_type=TaskType.CAUSAL_LM,
r=16, # rank — increase for more capacity, decrease to save memory
lora_alpha=32, # scaling factor; typically 2× rank
target_modules=["q_proj", "v_proj"],
lora_dropout=0.05,
bias="none",
)
model = get_peft_model(model, lora_config)
model.print_trainable_parameters() # verify: should be ~0.1–1% of total params
# 3. Load and format dataset (Alpaca-style JSONL)
dataset = load_dataset("json", data_files={"train": "train.jsonl", "test": "test.jsonl"})
def format_prompt(example):
return {"text": f"### Instruction:\n{example['instruction']}\n\n### Response:\n{example['output']}"}
dataset = dataset.map(format_prompt)
# 4. Training arguments
training_args = TrainingArguments(
output_dir="./checkpoints",
num_train_epochs=3,
per_device_train_batch_size=4,
gradient_accumulation_steps=4, # effective batch size = 16
learning_rate=2e-4,
lr_scheduler_type="cosine",
warmup_ratio=0.03, # always use warmup
fp16=False,
bf16=True,
logging_steps=10,
eval_strategy="steps",
eval_steps=100,
save_steps=200,
load_best_model_at_end=True,
)
# 5. Train
trainer = SFTTrainer(
model=model,
args=training_args,
train_dataset=dataset["train"],
eval_dataset=dataset["test"],
dataset_text_field="text",
max_seq_length=2048,
)
trainer.train()
# 6. Save adapter weights only
model.save_pretrained("./lora-adapter")
tokenizer.save_pretrained("./lora-adapter")
QLoRA variant — add these lines before loading the model to enable 4-bit quantization:
from transformers import BitsAndBytesConfig
bnb_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_compute_dtype=torch.bfloat16,
bnb_4bit_use_double_quant=True,
)
model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config, device_map="auto")
Merge adapter into base model for deployment:
from peft import PeftModel
base = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16)
merged = PeftModel.from_pretrained(base, "./lora-adapter").merge_and_unload()
merged.save_pretrained("./merged-model")
Constraints
MUST DO
- Validate dataset quality before training
- Use parameter-efficient methods for large models (>7B)
- Monitor training/validation loss curves
- Document hyperparameters and training config
- Version datasets and model checkpoints
- Always include a learning rate warmup
MUST NOT DO
- Skip data quality validation
- Overfit on small datasets — use regularisation (dropout, weight decay) and early stopping
- Merge incompatible adapters (mismatched rank, base model, or target modules)
- Deploy without evaluation against a held-out set and latency benchmark
Output Templates
When implementing fine-tuning, always provide:
- Dataset preparation script with validation logic (schema checks, token-length histogram, deduplication)
- Training configuration (full
TrainingArguments+LoraConfigblock, commented) - Evaluation script reporting perplexity, task-specific metrics, and latency
- Brief design rationale — why this PEFT method, rank, and learning rate were chosen for this task
Maintained by @jeffallan, Principal Consultant at Synergetic Solutions
FAQ
What does the fine-tuning-expert skill do?
Use when fine-tuning LLMs, training custom models, or adapting foundation models for specific tasks. Invoke for configuring LoRA/QLoRA adapters, preparing JSONL training datasets, setting hyperparameters for fine-tuning runs, adapter training, transfer learning, finetuning with Hugging Face PEFT, OpenAI fine-tuning, instruction tuning, RLHF, DPO, or quantizing and deploying fine-tuned models. Trigger terms include: LoRA, QLoRA, PEFT, finetuning, fine-tuning, adapter tuning, LLM training, model training, custom model.
How do I install fine-tuning-expert?
Run npx skills add https://github.com/jeffallan/claude-skills --skill fine-tuning-expert in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/fine-tuning-expert/ (personal) or .claude/skills/fine-tuning-expert/ (project).
Which AI agents can use fine-tuning-expert?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is fine-tuning-expert safe to install?
Security partners have reviewed it: Gen Agent Trust Hub flagged risks; Socket flagged items to review; Snyk flagged items to review; Runlayer flagged risks; ZeroLeaks passed. As with any skill, read the SKILL.md and bundled scripts before installing.
Who maintains fine-tuning-expert?
It is published by jeffallan in jeffallan/claude-skills. It has 4,266 recorded installs.
More from jeffallan/claude-skills
laravel-specialist
jeffallan/claude-skills
Build and configure Laravel 10+ applications, including creating Eloquent models and relationships, implementing Sanctum authentication, configuring Horizon queues, designing RESTful APIs with API resources, and building reactive interfaces with Livewire. Use when creating Laravel models, setting up queue workers, implementing Sanctum auth flows, building Livewire components, optimising Eloquent queries, or writing Pest/PHPUnit tests for Laravel features.
golang-pro
jeffallan/claude-skills
Implements concurrent Go patterns using goroutines and channels, designs and builds microservices with gRPC or REST, optimizes Go application performance with pprof, and enforces idiomatic Go with generics, interfaces, and robust error handling. Use when building Go applications requiring concurrent programming, microservices architecture, or high-performance systems. Invoke for goroutines, channels, Go generics, gRPC integration, CLI tools, benchmarks, or table-driven testing.
php-pro
jeffallan/claude-skills
Use when building PHP applications with modern PHP 8.3+ features, Laravel, or Symfony frameworks. Invokes strict typing, PHPStan level 9, async patterns with Swoole, and PSR standards. Creates controllers, configures middleware, generates migrations, writes PHPUnit/Pest tests, defines typed DTOs and value objects, sets up dependency injection, and scaffolds REST/GraphQL APIs. Use when working with Eloquent, Doctrine, Composer, Psalm, ReactPHP, or any PHP API development.
flutter-expert
jeffallan/claude-skills
Use when building cross-platform applications with Flutter 3+ and Dart. Invoke for widget development, Riverpod/Bloc state management, GoRouter navigation, platform-specific implementations, performance optimization.
typescript-pro
jeffallan/claude-skills
Implements advanced TypeScript type systems, creates custom type guards, utility types, and branded types, and configures tRPC for end-to-end type safety. Use when building TypeScript applications requiring advanced generics, conditional or mapped types, discriminated unions, monorepo setup, or full-stack type safety with tRPC.
kubernetes-specialist
jeffallan/claude-skills
Use when deploying or managing Kubernetes workloads. Invoke to create deployment manifests, configure pod security policies, set up service accounts, define network isolation rules, debug pod crashes, analyze resource limits, inspect container logs, or right-size workloads. Use for Helm charts, RBAC policies, NetworkPolicies, storage configuration, performance optimization, GitOps pipelines, and multi-cluster management.
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available