Instructions to use onnx-community/functiongemma-270m-it-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use onnx-community/functiongemma-270m-it-ONNX with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('text-generation', 'onnx-community/functiongemma-270m-it-ONNX');
Small experiment with FunctionGemma and Transformers.js
#2
by harlley - opened
I fine-tuned the model, but it didn’t work after exporting to ONNX format. However, the agentic UI is working well with the original FP16 version. Any help with the export would be greatly appreciated.
~> Demo: https://huggingface.co/spaces/harlley/basic-agentic-ui
harlley changed discussion status to closed
harlley changed discussion status to open
@harlley , check out this script by @Xenova : https://gist.github.com/xenova/a219dbf3c7da7edd5dbb05f92410d7bd
It worked for me, and kept the model much smaller than other ONNX export methods.