Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2408.04632 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909281761099776 |
|---|---|
| author | Borchmann, Łukasz Pietruszka, Michał Jaśkowski, Wojciech Jurkiewicz, Dawid Halama, Piotr Józiak, Paweł Garncarek, Łukasz Liskowski, Paweł Szyndler, Karolina Gretkowski, Andrzej Ołtusek, Julita Nowakowska, Gabriela Zawłocki, Artur Duhr, Łukasz Dyda, Paweł Turski, Michał |
| author_facet | Borchmann, Łukasz Pietruszka, Michał Jaśkowski, Wojciech Jurkiewicz, Dawid Halama, Piotr Józiak, Paweł Garncarek, Łukasz Liskowski, Paweł Szyndler, Karolina Gretkowski, Andrzej Ołtusek, Julita Nowakowska, Gabriela Zawłocki, Artur Duhr, Łukasz Dyda, Paweł Turski, Michał |
| contents | The vast portion of workloads employing LLMs involves answering questions grounded on PDF or scan content. We introduce the Arctic-TILT achieving accuracy on par with models 1000$\times$ its size on these use cases. It can be fine-tuned and deployed on a single 24GB GPU, lowering operational costs while processing Visually Rich Documents with up to 400k tokens. The model establishes state-of-the-art results on seven diverse Document Understanding benchmarks, as well as provides reliable confidence scores and quick inference, which are essential for processing files in large-scale or time-sensitive enterprise environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_04632 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Arctic-TILT. Business Document Understanding at Sub-Billion Scale Borchmann, Łukasz Pietruszka, Michał Jaśkowski, Wojciech Jurkiewicz, Dawid Halama, Piotr Józiak, Paweł Garncarek, Łukasz Liskowski, Paweł Szyndler, Karolina Gretkowski, Andrzej Ołtusek, Julita Nowakowska, Gabriela Zawłocki, Artur Duhr, Łukasz Dyda, Paweł Turski, Michał Computation and Language Computer Vision and Pattern Recognition The vast portion of workloads employing LLMs involves answering questions grounded on PDF or scan content. We introduce the Arctic-TILT achieving accuracy on par with models 1000$\times$ its size on these use cases. It can be fine-tuned and deployed on a single 24GB GPU, lowering operational costs while processing Visually Rich Documents with up to 400k tokens. The model establishes state-of-the-art results on seven diverse Document Understanding benchmarks, as well as provides reliable confidence scores and quick inference, which are essential for processing files in large-scale or time-sensitive enterprise environments. |
| title | Arctic-TILT. Business Document Understanding at Sub-Billion Scale |
| topic | Computation and Language Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.04632 |