tinker-fine-tuning

tinker-fine-tuning is a skill for Claude Code, Codex from synthetic-sciences/openscience. It costs 62 tokens per session (4,372 once invoked), scanned A, original, Apache-2.0.

A service and programming guide for fine-tuning supported language and vision-language models on managed cloud GPUs. It supports supervised training, LoRA adapters, and reinforcement-learning methods such as GRPO and PPO.

In plain words
What is it for?
Use it to train LoRA adapters, fine-tune supported language or vision-language models, and run custom GRPO or PPO training loops in the cloud.
Why use it?
It removes the need to provision and manage the GPU machines used for supported model-training jobs.

Skill for Claude CodeCodex

About the project

synthetic-sciences/openscience is an AI workbench that carries out scientific research by reading papers, forming hypotheses, writing and running code, conducting experiments, analyzing results, and preparing reports. Researchers use it for work in machine learning, biology, physics, and chemistry with remote or local models. Catalogue add-ons extend its scientific workflows through skills and instructions.

synthetic-sciences/openscience · 3,473 stars · on GitHub

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.

agentmods
npx agentmods add skills/synthetic-sciences/openscience/tinker
Any agent
npx skills add synthetic-sciences/openscience --skill tinker
Clone the repo
git clone --depth 1 https://github.com/synthetic-sciences/openscience

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 tinker-fine-tuning

README.md
[![agentmods](https://agentmods.dev/badge/skills/synthetic-sciences/openscience/tinker.svg)](https://agentmods.dev/skills/synthetic-sciences/openscience/tinker)
Your own site
<a href="https://agentmods.dev/skills/synthetic-sciences/openscience/tinker"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/tinker.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,372 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00062 $0.04372
Opus 5 $0.00031 $0.02186
Sonnet 5 $0.00012 $0.00874
Haiku 4.5 $0.00006 $0.00437

Measured yesterday against content hash dc6f6fa33901, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tinker-fine-tuning 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 yesterday.

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.

backend/cli/skills/cloud-compute/tinker/SKILL.md · 468 lines

How it starts

The opening of the file, as written. The whole thing — 468 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tinker API - Cloud LLM Fine-Tuning

Expert guidance for fine-tuning large language models using Tinker's managed cloud training API. Tinker handles GPU allocation, model hosting, and distributed training — you write the training logic, Tinker runs it on cloud infrastructure.

When to Use This Skill

Use Tinker when you need to:

  • Fine-tune models up to 235B parameters without managing GPU infrastructure
  • Run LoRA training on Qwen, Llama, DeepSeek, or GPT-OSS models
  • Train vision-language models (Qwen3-VL)
  • Implement custom RL loops (GRPO, PPO, importance sampling) on cloud GPUs
  • Iterate quickly with a training API that handles hardware provisioning

Do NOT use Tinker when:

  • You need full fine-tuning (not LoRA) — Tinker only supports LoRA
  • You need to train custom architectures — Tinker supports specific model families
  • You want to use your own GPUs — use Axolotl, Unsloth, or LLaMA-Factory instead
  • You need offline/air-gapped training

Tinker vs Alternatives:

Need Use
Managed cloud LoRA training Tinker
Local GPU fine-tuning Axolotl, Unsloth, LLaMA-Factory
Full parameter fine-tuning DeepSpeed + Transformers
RLHF with TRL locally TRL + GRPO skill
Quantized training Unsloth, bitsandbytes

Quick Reference

Topic Reference
Setup & Core Concepts Getting Started
API Classes & Types API Reference
Supervised Learning Supervised Learning
RL Training & Environments Reinforcement Learning
DPO, RLHF & Distillation DPO & Preference Learning
Loss Functions Loss Functions
Chat Templates Rendering
Models & LoRA Models & LoRA
Evaluations Evaluations
Example Scripts Recipes

Read the full file on GitHub · 468 lines

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. yesterday First seen · 468 lines · 62 tokens per session scan A dc6f6fa33901

Subscribe to this mod's changes

tinker-fine-tuning is a skill published in the GitHub repository synthetic-sciences/openscience (3,473 stars, last pushed today), licensed Apache-2.0. It adds 62 tokens to every session and 4,372 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.

Related

Other skills, from other repositories

fine-tuning-with-trl

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

davila7/claude-code-templates · 69 tokens

fine-tuning-with-trl

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

OpenLAIR/dr-claw · 69 tokens

fine-tuning-with-trl

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

Orchestra-Research/AI-Research-SKILLs · 69 tokens

fine-tuning-with-trl

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

liortesta/ClawdAgent · 69 tokens

model_finetuning

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

vuralserhat86/antigravity-agentic-skills · 67 tokens

fine-tuning-with-trl

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

ihatesea69/HieuNghi-AI-Skills · 69 tokens