Image-Text-to-Text
Transformers.js
ONNX
florence2
vision
text-generation
text2text-generation
image-to-text
Instructions to use onnx-community/Florence-2-base-ft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use onnx-community/Florence-2-base-ft with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('image-text-to-text', 'onnx-community/Florence-2-base-ft');
Mismatched `inputs_embeds` and `logits` shape for decoder_with_past and other decoders?
#9
by carlesonielfa - opened
Hi! Thanks for uploading the conversion to ONNX. I'm trying to use this on a Triton server where the merged graph does not seem to be supported. However, I can see that for the decoder_with_past the shapes are
inputs_embeds [batch_size,16,768]logits [batch_size, 16, 51289]
And for the decoder and decoder_merged exports the shapes are
inputs_embeds [batch_size, decoder_sequence_length, 768]logits [batch_size,decoder_sequence_length,51289]
Is this right? Thank you in advance!
Same error