unsloth-hf-jobs

unsloth-hf-jobs is a skill for Claude Code, Codex from svngoku/coding-agents-skills. It costs 111 tokens per session (1,487 once invoked), scanned C, original, MIT.

A set of scripts for fine-tuning language and vision-language models with Unsloth on Hugging Face Jobs, a service that runs jobs on rented cloud GPUs.

In plain words
What is it for?
Fine-tuning language models, training models that understand images and text, continued pretraining, adapting models to a specific field, and running UV scripts on Hugging Face Jobs.
Why use it?
It provides ready-made training scripts and automatically handles their Python dependencies, reducing setup work for remote GPU training.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Fine-tuning language models, training models that understand images and text, continued pretraining, adapting models to a specific field, and running UV scripts on Hugging Face Jobs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/svngoku/coding-agents-skills/unsloth-hf-jobs
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 svngoku/coding-agents-skills --skill unsloth-hf-jobs
Clone the repo
git clone --depth 1 https://github.com/svngoku/coding-agents-skills

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 unsloth-hf-jobs

README.md
[![agentmods](https://agentmods.dev/badge/skills/svngoku/coding-agents-skills/unsloth-hf-jobs/github.svg)](https://agentmods.dev/skills/svngoku/coding-agents-skills/unsloth-hf-jobs)
Your own site
<a href="https://agentmods.dev/skills/svngoku/coding-agents-skills/unsloth-hf-jobs"><img src="https://agentmods.dev/badge/skills/svngoku/coding-agents-skills/unsloth-hf-jobs/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 unsloth-hf-jobs

Your own site · 80×15
<a href="https://agentmods.dev/skills/svngoku/coding-agents-skills/unsloth-hf-jobs"><img src="https://agentmods.dev/badge/skills/svngoku/coding-agents-skills/unsloth-hf-jobs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,487 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00111 $0.01487
Opus 5 $0.00056 $0.00744
Sonnet 5 $0.00022 $0.00297
Haiku 4.5 $0.00011 $0.00149

Measured 12d ago against content hash 0775132b8dd7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

unsloth-hf-jobs scanned grade C with 2 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 12d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (graders/check.py, scripts/continued-pretraining.py, scripts/sft-gemma3-vlm.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

- HF CLI: `curl -LsSf https://hf.co/cli/install.sh | bash`

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- HF CLI: `curl -LsSf https://hf.co/cli/install.sh | bash`
skills/unsloth-hf-jobs/SKILL.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Unsloth Training on HF Jobs

Fine-tune LLMs and VLMs using Unsloth on HF Jobs with UV scripts that handle dependencies automatically.

Prerequisites

  • Hugging Face account with token
  • HF CLI: curl -LsSf https://hf.co/cli/install.sh | bash
  • Dataset on the Hub (see data formats below)

Available Scripts

Script Base Model Task
scripts/sft-qwen3-vl.py Qwen3-VL-8B VLM fine-tuning
scripts/sft-gemma3-vlm.py Gemma 3 4B VLM fine-tuning (smaller)
scripts/continued-pretraining.py Qwen3-0.6B Domain adaptation

Remote URL (for HF Jobs): https://huggingface.co/datasets/uv-scripts/unsloth-jobs/raw/main/

Data Formats

VLM Fine-tuning

Requires images and messages columns:

{
    "images": [<PIL.Image>],
    "messages": [
        {"role": "user", "content": [{"type": "image"}, {"type": "text", "text": "What's in this image?"}]},
        {"role": "assistant", "content": [{"type": "text", "text": "A golden retriever playing fetch."}]}
    ]
}

Example dataset: davanstrien/iconclass-vlm-sft

Continued Pretraining

Any dataset with a text column (use --text-column if named differently):

{"text": "Your domain-specific text here..."}

Usage Patterns

VLM Fine-tuning

hf jobs uv run \
  https://huggingface.co/datasets/uv-scripts/unsloth-jobs/raw/main/sft-qwen3-vl.py \
  --flavor a100-large --secrets HF_TOKEN --timeout 4h \
  -- --dataset <username>/<dataset> \
     --num-epochs 1 \
     --eval-split 0.2 \
     --output-repo <username>/<model-name>

Continued Pretraining

hf jobs uv run \
  https://huggingface.co/datasets/uv-scripts/unsloth-jobs/raw/main/continued-pretraining.py \
  --flavor a100-large --secrets HF_TOKEN \
  -- --dataset <username>/<dataset> \
     --text-column content \
     --max-steps 1000 \
     --output-repo <username>/<model-name>

Read the full file on GitHub · 134 lines

Files

What ships with it

8 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. 12d ago First seen · 134 lines · 111 tokens per session scan C 0775132b8dd7

Subscribe to this mod's changes

unsloth-hf-jobs is a skill published in the GitHub repository svngoku/coding-agents-skills (11 stars, last pushed 29d ago), licensed MIT. It adds 111 tokens to every session and 1,487 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

iflytek-image-understanding

An image-analysis tool that describes pictures and answers questions about what they contain. It uses an AI vision service, which interprets visual content rather than only reading text files.

iflytek/iFly-Skills · 61 tokens

multi-agent-orchestration

Expert guide for designing and orchestrating multi-agent systems, agent swarms, 2026 Anthropic agentic design patterns, graph-based workflows (LangGraph, OpenAI Agents SDK, Google ADK, Mastra.ai), shared state memory, and human-in-the-loop guardrails in English and Indonesian.

roedyrustam/vibes-plug · 67 tokens

ai-media-generation-expert

Expert guide for AI image generation (Flux, DALL-E, Stable Diffusion), video generation (Sora, Runway), voice synthesis (ElevenLabs TTS), and speech recognition (Whisper STT) integration / Panduan ahli integrasi AI generasi gambar, video, suara (TTS), dan pengenalan suara (STT).

roedyrustam/vibes-plug · 78 tokens

vector-db-rag-expert

Expert guide for high-performance Vector Databases, Deep RAG architectures, pgvector 0.8+ HNSW, Reciprocal Rank Fusion (RRF), Cross-Encoder Re-ranking, and Late Chunking / Panduan ahli Vector DB, arsitektur Deep RAG, pgvector HNSW, RRF, dan Re-ranking.

roedyrustam/vibes-plug · 77 tokens

ai-llm-integration-expert

Expert guide for integrating Large Language Models (LLMs), Model Context Protocol (MCP v1.x), hybrid reasoning models, RAG architecture, vector databases, and AI agents / Panduan ahli untuk integrasi LLM, Model Context Protocol (MCP), model hybrid reasoning, arsitektur RAG, vector database, dan agen AI.

roedyrustam/vibes-plug · 78 tokens

ai-prompt-engineering-expert

Expert guide for Prompt Engineering, Chain-of-Thought, few-shot prompting, structured output, prompt injection defense, and automated AI evaluations & regression benchmarking (Promptfoo, DeepEval) / Panduan ahli rekayasa prompt dan evaluasi otomatis AI.

roedyrustam/vibes-plug · 58 tokens