VIBETHINKER · WEBGPU TRAIN + HOT-SWAP LoRA

Train VibeThinker-3B in your browser — full WebGPU backward pass + AdamW over the int4 base — then hot-swap the LoRA into inference live. No server. No upload.
🎮 Act
🗺 Learn
🧍
🌐 The open web
» Roaming the web — visit a service in LEARN to acquire your first skill.
⚙ Inference is paused while VibeThinker-3B is learning in the Train tab…
Model not loaded Press “Load VibeThinker-3B” to begin. First load streams the weights once, then it's cached.
Step 1 · Install the model
~6 GB, one-time — streamed from Hugging Face & cached in your browser. Other sources under ⚙.

🗺 Travel the web and learn a skill from a service you use. Each one is a LoRA trained entirely in this tab that compiles a plain request into a precise macro over a small, typed action space — constrained codegen (the model's strength), not chat. Pick a destination to learn:

⚔ Inbox & Calendar skill

    Forge a custom skill from your own text

    Paste the private text you would never send to a cloud model — notes, decision rules, your own action vocabulary — and the skill is trained locally. For strongest results, include explicit rules, examples, or acceptance criteria the model can reason over. Everything stays local to this browser session unless you export it.

    ① Build & tokenize
    ② Forward
    ③ Backward (grads)
    ④ AdamW update
    ⑤ Hot-swap live
    Done. The tuned adapter is live and saved to your fine-tunes. Open it in Inference.
    In-browser WebGPU training · full backward + AdamW · runtime LoRA hot-swap. 🜂 · model · source