finetune-llm-llama-factory

finetune-llm-llama-factory is a skill for Claude Code, Codex from Seeed-Projects/Seeed-Jetson-DevelopTool. It costs 72 tokens per session (857 once invoked), scanned B, original, MIT.

A deployment guide for Llama-Factory, a tool for adapting language models with example data, on an NVIDIA Jetson computer. It installs the tool through jetson-examples and opens its training interface in a browser.

In plain words
What is it for?
Fine-tuning a model such as Phi-1.5 with the alpacazh dataset on Jetson devices with at least 16GB of RAM. It covers launching the service, using its web interface, and testing the fine-tuned model.
Why use it?
It removes much of the setup needed to start model training on Jetson hardware. The guide provides a ready deployment command and a way to test the resulting model.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Fine-tuning a model such as Phi-1.5 with the alpacazh dataset on Jetson devices with at least 16GB of RAM. It covers launching the service, using its web interface, and testing the fine-tuned model.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/seeed-projects/seeed-jetson-developtool/finetune-llm-llama-factory
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.

Any agent
npx skills add Seeed-Projects/Seeed-Jetson-DevelopTool --skill finetune-llm-llama-factory
Clone the repo
git clone --depth 1 https://github.com/Seeed-Projects/Seeed-Jetson-DevelopTool

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 finetune-llm-llama-factory

README.md
[![agentmods](https://agentmods.dev/badge/skills/seeed-projects/seeed-jetson-developtool/finetune-llm-llama-factory/github.svg)](https://agentmods.dev/skills/seeed-projects/seeed-jetson-developtool/finetune-llm-llama-factory)
Your own site
<a href="https://agentmods.dev/skills/seeed-projects/seeed-jetson-developtool/finetune-llm-llama-factory"><img src="https://agentmods.dev/badge/skills/seeed-projects/seeed-jetson-developtool/finetune-llm-llama-factory/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.

agentmods 80×15 button for finetune-llm-llama-factory

Your own site · 80×15
<a href="https://agentmods.dev/skills/seeed-projects/seeed-jetson-developtool/finetune-llm-llama-factory"><img src="https://agentmods.dev/badge/skills/seeed-projects/seeed-jetson-developtool/finetune-llm-llama-factory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 857 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Privilege Escalation · line 34
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
  • medium Privilege Escalation · line 93
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
How audits are shown
Origin original No closer match found 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 $0.00072 $0.00857
Opus 5 $0.00036 $0.00428
Sonnet 5 $0.00014 $0.00171
Haiku 4.5 $0.00007 $0.00086

Measured 11d ago against content hash 4555dd6bf191, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

finetune-llm-llama-factory scanned grade B with 1 finding 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 11d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo reboot
seeed_jetson_develop/skills/openclaw/finetune-llm-llama-factory/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fine-tune LLM with Llama-Factory on Jetson


Execution model

Run one phase at a time. After each phase:

  • Relay all command output to the user.
  • If output contains [STOP] → stop immediately, consult the failure decision tree below.
  • If output ends with [OK] → tell the user "Phase N complete" and proceed to the next phase.

Prerequisites

Requirement Details
Hardware Jetson device with ≥16GB RAM (tested on Orin NX 16GB and AGX Orin 64GB)
Peripherals Monitor, mouse, keyboard, network (optional but recommended)
JetPack 5.x or 6.x
Internet Required for initial container pull

Phase 1 — Install jetson-examples (~2 min)

pip3 install jetson-examples
sudo reboot

[OK] after reboot completes and you can log back in.


Phase 2 — Deploy Llama-Factory (~5–15 min)

Launch Llama-Factory using the one-line deployment:

reComputer run llama-factory

This pulls the container and starts the Llama-Factory service.

Once running, open a web browser and navigate to:

http://127.0.0.1:7860

(Or replace 127.0.0.1 with the Jetson's IP for remote access.)

[OK] when the Llama-Factory WebUI loads in the browser. [STOP] if the container fails to start.


Phase 3 — Start training (~18 hours for default config)

In the WebUI:

  1. Set Model name to Phi-1.5 (or your chosen model)
  2. Set Dataset to alpaca_zh (or your chosen dataset)
  3. Keep other training parameters as default
  4. Click the Start button

Monitor training progress in the WebUI.

[OK] when training completes and the fine-tuned model appears in the save directory.


Phase 4 — Test the fine-tuned model (~2 min)

In the Llama-Factory WebUI:

  1. Navigate to the Chat tab
  2. Load the fine-tuned model by selecting the checkpoint path
  3. Enter a prompt in the Input text box (e.g. a Chinese language prompt if using alpaca_zh)
  4. Click Submit and check the output in the Chatbot text box

[OK] when the model responds with coherent output reflecting the fine-tuning data.

Read the full file on GitHub · 105 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 105 lines · 72 tokens per session scan B 4555dd6bf191

Subscribe to this mod's changes

finetune-llm-llama-factory is a skill published in the GitHub repository Seeed-Projects/Seeed-Jetson-DevelopTool (55 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 857 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

google-cloud-solution-agentic-analytics-spark-knowledge-catalog

Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…

google/skills · 138 tokens

training-check

Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.

wanshuiyin/Auto-claude-code-research-in-sleep · 35 tokens

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

NVIDIA/skills · 30 tokens