Prism OS command center model

FunctionGemma 270M fine-tuned on the commands of Prism OS, a desktop in the browser whose window manager is a handwired numeric program. It turns a sentence into Prism OS's function calls, or a short reply. It runs in the browser with Transformers.js on WebGPU (onnx/model_q4f16.onnx, the graph of onnx-community/functiongemma-270m-it-ONNX with these weights). The PyTorch weights are in pytorch/.

Results on held-out phrasings

Every eval sentence uses a phrasing template that never appears in training. The checkpoint kept was the best on a separate dev set of eval sentences, which these scores leave out.

Model Correct
Base FunctionGemma 108/746
Fine-tuned (PyTorch, bf16) 701/746
Fine-tuned, browser build (q4f16), first 100 95/100

Use is subject to the Gemma Terms of Use.

Downloads last month
351
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for AppleLampsX/prism-os-functiongemma

Quantized
(66)
this model