Why did we open-source our inference engine? Read the post

← Catalog

microsoft/Florence-2-base

Open comparison →

Primitive: /extract · Extract · Florence-2

This Hub repository contains a HuggingFace's `transformers` implementation of Florence-2 model from Microsoft.

MultimodalText regions

Overview

Hardware: — drives latency, throughput & cost

Size232M params
Tasks /extract
Licensemit
Latency
Throughput
Cost /1M tok

Cost is approximate — computed from list GPU prices; your actual price depends on the provider you deploy SIE with.

Extraction

Output kindstext_regions
Inputsimage
Max sequence length

Benchmarks

CORD v2

general kie en

Key information extraction from receipt images

Corpus: 100 Queries: 100
Quality
f1 0.0000
Reference →

Open source inference for agents

Open-source inference for the models behind your agents. Run it yourself, or let us run it for you.

Github 2.3K

Contact us

Tell us about your use case and we'll get back to you shortly.

Apply for an inference grant

Free capacity on our hosted cluster for selected projects. Tell us what you run and we reply by email.