All skills
agent-platform-tuning
Fine-tune open or Gemini models on Agent Platform, from dataset prep through job monitoring and deployment.
- Part of google/skills
- 10k installs
- Machine Learning · Fine-tuning and quantization
When to use it
You have a JSONL dataset and a Google Cloud project but still need to configure, submit, and track a tuning job.
For example
You say
Use agent-platform-tuning to fine-tune google/gemma3@gemma-3-12b-it on my JSONL dataset in gs://my-bucket/tune, project my-proj, region global.
You get
- Column mapping confirmation
- Tuning job config
- Job status summary
How it works
- Recommends a supported model from its catalog and explains trade-offs before configuring.
- For open models it proposes the global location, which picks a region with available capacity.
Before installing
Requires a Google Cloud project and region, plus gcloud CLI access with Agent Platform and Cloud Storage APIs enabled.
This skill includes 6 scripts your assistant may run on your computer.
More Fine-tuning and quantization skills
See all- fine-tuning-expert4.6kHelps fine-tune language models with LoRA adapters, training datasets, hyperparameters and deployment.
- ruview-model-training25Trains, fine-tunes and publishes RuView pose and embedding models, including GPU training and Hugging Face uploads.
- unsloth25Fine-tunes models 2-5x faster with LoRA or QLoRA while using less VRAM.
- hugging-face-model-trainer23Trains and fine-tunes language models with TRL on Hugging Face Jobs, covering SFT, DPO, GRPO, and GGUF conversion.
Also in this pack
- cloud-run-basics19.4kDeploys and manages Cloud Run services, jobs and worker pools.
- gemini-api18.8kWrites code that calls Gemini models for text, images, video, audio, embeddings and more across languages.
- google-cloud-recipe-auth17.1kExplains how to authenticate and authorize users and services to Google Cloud APIs, including IAM and ADC.
- google-cloud-recipe-onboarding16.9kWalks a new developer through creating a Google Cloud account, setting up billing and deploying a first resource.