◉ Checking local model...
Add Model · Ollama
Downloads from the internet into Ollama's local model store. Check available disk space and model licensing before installing. Model files may be several GB.
Model installation is optional.
Advanced: Personal Fine-Tuning ProviderYour provider account
Connect and review your own provider account. The provider bills you directly; this Lab does not hold a shared GPU account or payment method.
RunPod API tokens and SSH public keys are credentials that only enable a direct connection to your own RunPod account or an already-running server. By themselves, they cannot create a server, start a job, or charge your account. Use the official RunPod Console to connect to and manage your own RunPod servers; the Lab cannot create a provider resource or charge your account.
Open RunPod Console ↗
OpenAI API keys are not accepted, stored, or used by this Lab. Instead, you may optionally connect with ChatGPT through your browser. This user-approved connection does not use an API key. Connecting alone does not send prompts, make an AI request, or create a charge.
Open OpenAI API Platform ↗
Optional: Sign in with ChatGPT
Use your browser to approve a direct connection to your own ChatGPT account. The resulting connection record is protected locally for this Windows user. Connecting does not send a prompt or invoke a model. After connection, you may explicitly ask the external advisor for help with material you choose to share.
Checking local ChatGPT connection status…
External ChatGPT advisor
Online text chat for explicit reviews. This advisor is separate from the local agents.
Privacy status: while this connection remains active, the Lab is not exclusively local because it has an enabled OpenAI connection. No room content leaves the device until you explicitly submit one of the options below. Disconnect ChatGPT locally to return to local-only operation.
Only the material selected below leaves this device for OpenAI. Local agents keep working through local Ollama in parallel. Do not include private material unless you choose to share it.
Set a plan, then connect your own provider account. No paid job is started automatically.
Optional: save a RunPod access token for this Windows user
Your token is encrypted locally with Windows protection. It is never shown again by the Lab. It is used only when you explicitly check your own provider connection; saving it never starts a paid job.
Checking local credential status…
Check your RunPod account
Checks your encrypted token and reads current GPU availability and listed prices from your RunPod account. It cannot create a Pod, upload data, or charge your account.
No connection check has been run.
What is Fine-Tuning? A simple guide ?