← 返回 Skills 市场
754
总下载
2
收藏
5
当前安装
1
版本数
在 OpenClaw 中安装
/install fine-tuning
功能描述
Fine-tune LLMs with data preparation, provider selection, cost estimation, evaluation, and compliance checks.
使用说明 (SKILL.md)
When to Use
User wants to fine-tune a language model, evaluate if fine-tuning is worth it, or debug training issues.
Quick Reference
| Topic | File |
|---|---|
| Provider comparison & pricing | providers.md |
| Data preparation & validation | data-prep.md |
| Training configuration | training.md |
| Evaluation & debugging | evaluation.md |
| Cost estimation & ROI | costs.md |
| Compliance & security | compliance.md |
Core Capabilities
- Decide fit — Analyze if fine-tuning beats prompting for the use case
- Prepare data — Convert raw data to JSONL, deduplicate, validate format
- Select provider — Compare OpenAI, Anthropic (Bedrock), Google, open source based on constraints
- Estimate costs — Calculate training cost, inference savings, break-even point
- Configure training — Set hyperparameters (learning rate, epochs, LoRA rank)
- Run evaluation — Compare fine-tuned vs base model on task-specific metrics
- Debug failures — Diagnose loss curves, overfitting, catastrophic forgetting
- Handle compliance — Scan for PII, configure on-premise training, generate audit logs
Decision Checklist
Before recommending fine-tuning, ask:
- What's the failure mode with prompting? (format, style, knowledge, cost)
- How many training examples available? (minimum 50-100)
- Expected inference volume? (affects ROI calculation)
- Privacy constraints? (determines provider options)
- Budget for training + ongoing inference?
Fine-Tune vs Prompt Decision
| Signal | Recommendation |
|---|---|
| Format/style inconsistency | Fine-tune ✓ |
| Missing domain knowledge | RAG first, then fine-tune if needed |
| High inference volume (>100K/mo) | Fine-tune for cost savings |
| Requirements change frequently | Stick with prompting |
| \x3C50 quality examples | Prompting + few-shot |
Critical Rules
- Data quality > quantity — 100 great examples beat 1000 noisy ones
- LoRA first — Never jump to full fine-tuning; LoRA is 10-100x cheaper
- Hold out eval set — Always 80/10/10 split; never peek at test data
- Same precision — Train and serve at identical precision (4-bit, 16-bit)
- Baseline first — Run eval on base model before training to measure actual improvement
- Expect iteration — First attempt rarely optimal; plan for 2-3 cycles
Common Pitfalls
| Mistake | Fix |
|---|---|
| Training on inconsistent data | Manual review of 100+ samples before training |
| Learning rate too high | Start with 2e-4 for SFT, 5e-6 for RLHF |
| Expecting new knowledge | Fine-tuning adjusts behavior, not knowledge — use RAG |
| No baseline comparison | Always test base model on same eval set |
| Ignoring forgetting | Mix 20% general data to preserve capabilities |
安全使用建议
This skill is a comprehensive fine-tuning guide but is missing explicit declarations of operational needs. Before installing/using it: 1) Expect to need provider credentials (OpenAI key, AWS creds for Bedrock, Hugging Face token) and ensure you only provide those in a controlled environment; the skill metadata does not list them. 2) Be careful with real datasets: the examples upload local data to remote APIs and could send PII to third parties — follow the compliance.md PII-remediation steps and test on non-sensitive samples first. 3) The skill is instruction-only (no install) so it won't auto-run code, but following its examples will run CLI/SDK commands and pip installs — review commands before executing and prefer isolated/sandboxed environments. 4) If you require strict privacy, prefer the on‑prem instructions in compliance.md and verify how to authenticate and download models offline. 5) Because the source/homepage is unknown, exercise extra caution: verify code snippets and provider commands against official provider docs before use.
功能分析
Type: OpenClaw Skill
Name: fine-tuning
Version: 1.0.0
The OpenClaw AgentSkills skill bundle is benign. All files (SKILL.md, compliance.md, costs.md, data-prep.md, evaluation.md, providers.md, training.md) contain documentation and code snippets directly related to fine-tuning Large Language Models. The Python and Bash code examples demonstrate standard, legitimate operations such as data validation, deduplication, model training with libraries like Unsloth, interaction with OpenAI APIs for fine-tuning, and local package/model downloads for air-gapped environments. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, prompt injection with harmful intent, or obfuscation. The content is purely instructional and functional for its stated purpose.
能力评估
Purpose & Capability
The name/description match the provided files: the SKILL.md and supporting docs are a thorough fine-tuning playbook (data prep, providers, costs, evaluation, compliance). The requested capabilities are appropriate for a fine-tuning helper.
Instruction Scope
The runtime instructions and example code assume use of provider SDKs/CLIs (OpenAI client/CLI, Bedrock, huggingface-cli, pip installs/transfers for air-gapped systems) and local dataset files. The SKILL metadata declares no required env vars or credentials, yet the instructions require API keys, CLI auth, access to local dataset files, and network access to cloud providers — a scope mismatch. The docs also show uploading datasets and calling model endpoints which would transmit potentially sensitive data to third-party providers if the user follows examples.
Install Mechanism
This is instruction-only (no install spec), so nothing will be automatically written or executed by installation. However, the docs instruct users to run package installs, pip downloads, huggingface and OpenAI CLI commands and to pre-download model artifacts for air-gapped setups — all of which require manual actions and network access. There is no automatic installer, which lowers supply-chain risk but does not remove runtime risks if users execute the suggested commands.
Credentials
The registry metadata lists no required environment variables or primary credential, yet multiple code snippets and CLI commands clearly require provider credentials (OPENAI API keys, AWS credentials for Bedrock/Bedrock via AWS, Hugging Face auth) and may encourage enabling 'data sharing' discounts. Asking users to run these without declaring them is a transparency gap. The compliance guidance also emphasizes scanning/removing PII, but example eval/generation snippets call out to remote providers (client.chat/completions.create), which would send dataset content off-host unless an on-prem option is used.
Persistence & Privilege
The skill is not always-enabled and does not request special persistence or system-wide changes. It does not modify other skills or claim elevated privileges. Autonomous invocation is allowed (platform default) but is not combined with other major red flags here.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install fine-tuning - 安装完成后，直接呼叫该 Skill 的名称或使用
/fine-tuning触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release
元数据
常见问题
Fine-Tuning 是什么？
Fine-tune LLMs with data preparation, provider selection, cost estimation, evaluation, and compliance checks. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 754 次。
如何安装 Fine-Tuning？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install fine-tuning」即可一键安装，无需额外配置。
Fine-Tuning 是免费的吗？
是的，Fine-Tuning 完全免费（开源免费），可自由下载、安装和使用。
Fine-Tuning 支持哪些平台？
Fine-Tuning 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Fine-Tuning？
由 Iván（@ivangdavila）开发并维护，当前版本 v1.0.0。
推荐 Skills