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

← Catalog

naver-clova-ix/donut-base-finetuned-cord-v2

Open comparison →

Primitive: /extract · Extract · Encoder-Decoder

Donut model fine-tuned on CORD. It was introduced in the paper OCR-free Document Understanding Transformer by Geewok et al. and first released in this repository.

MultimodalText regions

Overview

Hardware: — drives latency, throughput & cost

Size110M params
Tasks /extract
Licensemit
Latency8.4 s
Throughput757 tok/s
Cost$0.294 /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 0.1123
Performance L4 b1 c16
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.