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 agentmods add skills/synthetic-sciences/openscience/colab-finetuningnpx skills add synthetic-sciences/openscience --skill colab-finetuninggit clone --depth 1 https://github.com/synthetic-sciences/openscienceWrote 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/synthetic-sciences/openscience/colab-finetuning)<a href="https://agentmods.dev/skills/synthetic-sciences/openscience/colab-finetuning"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/colab-finetuning.svg" alt="Measured on agentmods" 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 | $0.00067 | $0.01542 |
| Opus 5 | $0.00034 | $0.00771 |
| Sonnet 5 | $0.00013 | $0.00308 |
| Haiku 4.5 | $0.00007 | $0.00154 |
Grade A, and why
colab-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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Colab Fine-Tuning
Fine-tune LLMs using Google Colab GPUs directly from the openscience CLI. Connect to free or paid Colab runtimes and run Unsloth training workflows remotely.
When to Use Colab Fine-Tuning
Use Colab when:
- You don't have a local GPU but need to fine-tune a model
- You want free GPU access (T4 with 15GB VRAM on Colab Free)
- Training models up to ~14B parameters (4-bit QLoRA)
- Quick experiments and prototyping before scaling to cloud
- Colab Pro/Pro+ for A100 (40-80GB) access
Don't use Colab when:
- You need persistent long-running jobs (>12h) — use Tinker or cloud providers
- Training 70B+ models — use Lambda, RunPod, or multi-GPU cloud
- You need guaranteed uptime — Colab may disconnect idle sessions
- Production training pipelines — use managed services
Colab vs Alternatives:
| Need | Use |
|---|---|
| Free GPU, quick experiments | Google Colab |
| Managed cloud training (any size) | Tinker |
| Persistent multi-GPU training | Lambda / RunPod |
| Local GPU available | Unsloth directly |
| Enterprise with SLA | Colab Enterprise (Vertex AI) |
Quick Start
Step 1: Generate Bridge Notebook
Use colab_notebook tool with workflow="bridge"
This creates a openscience-bridge.ipynb file that establishes a WebSocket tunnel between openscience and the Colab GPU.
Step 2: Open in Colab
- Go to colab.research.google.com
- Upload the bridge notebook (File → Upload notebook)
- Select GPU runtime (Runtime → Change runtime type → T4 GPU)
- Run all cells
- Copy the WebSocket URL that appears
Step 3: Connect from openscience
Use colab_connect tool with connection_url="wss://..."
Step 4: Run Training
Use colab_finetune tool with:
workflow: "sft"
model: "unsloth/Qwen3-4B-unsloth-bnb-4bit"
dataset: "mlabonne/FineTome-100k"
Or execute individual cells:
Use colab_execute tool with code="import torch; print(torch.cuda.get_device_name(0))"
What ships with it
3 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.
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.
- today First seen · 155 lines · 67 tokens per session scan A 55a009743d47
colab-finetuning is a skill published in the GitHub repository synthetic-sciences/openscience (3,432 stars, last pushed today), licensed Apache-2.0. It adds 67 tokens to every session and 1,542 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
axolotl
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support.
unsloth
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization.
data-validation-first
Use this skill before any data analysis, transformation, or modeling. Always inspect and validate the data before drawing conclusions or writing transformations.
input-validation-and-sanitization
Use this skill when implementing any endpoint, form handler, CLI tool, or function that accepts external input. Validate and sanitize all untrusted data before processing — never assume input is safe.
robust-error-handling-in-scripts
Use this skill when writing shell scripts, Python automation, or any unattended batch job. Ensure failures are detected, logged, and handled — never silently ignored.
structured-logging-and-observability
Use this skill when building production services, pipelines, or automation that needs to be debugged, monitored, or audited. Add structured logs, metrics, and health checks before shipping any service.