controlllmai/Florence-2-base-ft
By controlllmai · ↓ 9 · ♥ 0 · Updated 2026-03-15
What's in this repo
This page lists the files in controlllmai/Florence-2-base-ft, including decoder_model.onnx, decoder_model_bnb4.onnx, decoder_model_fp16.onnx and more.
- 48 ONNX models (.onnx files)
- 59 files, including 48 .onnx, 8 .json, 1 .md, 1 .txt
- Last updated 2026-03-15
ONNX files
| File | Size | Download |
|---|---|---|
| onnx/decoder_model.onnx | — | Download |
| onnx/decoder_model_bnb4.onnx | — | Download |
| onnx/decoder_model_fp16.onnx | — | Download |
| onnx/decoder_model_int8.onnx | — | Download |
| onnx/decoder_model_merged.onnx | — | Download |
| onnx/decoder_model_merged_bnb4.onnx | — | Download |
| onnx/decoder_model_merged_fp16.onnx | — | Download |
| onnx/decoder_model_merged_int8.onnx | — | Download |
| onnx/decoder_model_merged_q4.onnx | — | Download |
| onnx/decoder_model_merged_q4f16.onnx | — | Download |
Showing 10 of 48 .onnx files — see the full file list on the right.
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
https://huggingface.co/microsoft/Florence-2-base-ft with ONNX weights to be compatible with Transformers.js.
Usage (Transformers.js)
If you haven't already, you can install the Transformers.js JavaScript library from NPM using:
npm i @huggingface/transformers
Example: Perform image captioning with onnx-community/Florence-2-base-ft.
import {
Florence2ForConditionalGeneration,
AutoProcessor,
load_image,
} from '@huggingface/transformers';
// Load model, processor, and tokenizer
const model_id = 'onnx-community/Florence-2-base-ft';
const model = await Florence2ForConditionalGeneration.from_pretrained(model_id, { dtype: 'fp32' });
const processor = await AutoProcessor.from_pretrained(model_id);
// Load image and prepare vision inputs
const url = 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg';
const image = await load_image(url);
// Specify task and prepare text inputs
const task = '<MORE_DETAILED_CAPTION>';
const prompts = processor.construct_prompts(task);
// Pre-process the image and text inputs
const inputs = await processor(image, prompts);
// Generate text
const generated_ids = await model.generate({
...inputs,
max_new_tokens: 100,
});
// Decode generated text
const generated_text = processor.batch_decode(generated_ids, { skip_special_tokens: false })[0];
// Post-process the generated text
const result = processor.post_process_generation(generated_text, task, image.size);
console.log(result);
// { '<MORE_DETAILED_CAPTION>': 'A green car is parked in front of a tan building. There is a brown door on the building behind the car. There are two windows on the front of the building. ' }
We also released an online demo, which you can try yourself: https://huggingface.co/spaces/Xenova/florence2-webgpu
Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using 🤗 Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).
Model info
Created: 2026-03-15
Updated: 2026-03-15
View on Hugging FaceFiles (59)
Related models
More from controlllmai
No other models by this author.