Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2404.12387 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916238066712576 |
|---|---|
| author | Reka Team Ormazabal, Aitor Zheng, Che d'Autume, Cyprien de Masson Yogatama, Dani Fu, Deyu Ong, Donovan Chen, Eric Lamprecht, Eugenie Pham, Hai Ong, Isaac Aleksiev, Kaloyan Li, Lei Henderson, Matthew Bain, Max Artetxe, Mikel Relan, Nishant Padlewski, Piotr Liu, Qi Chen, Ren Phua, Samuel Yang, Yazheng Tay, Yi Wang, Yuqi Zhu, Zhongkai Xie, Zhihui |
| author_facet | Reka Team Ormazabal, Aitor Zheng, Che d'Autume, Cyprien de Masson Yogatama, Dani Fu, Deyu Ong, Donovan Chen, Eric Lamprecht, Eugenie Pham, Hai Ong, Isaac Aleksiev, Kaloyan Li, Lei Henderson, Matthew Bain, Max Artetxe, Mikel Relan, Nishant Padlewski, Piotr Liu, Qi Chen, Ren Phua, Samuel Yang, Yazheng Tay, Yi Wang, Yuqi Zhu, Zhongkai Xie, Zhihui |
| contents | We introduce Reka Core, Flash, and Edge, a series of powerful multimodal language models trained from scratch by Reka. Reka models are able to process and reason with text, images, video, and audio inputs. This technical report discusses details of training some of these models and provides comprehensive evaluation results. We show that Reka Edge and Reka Flash are not only state-of-the-art but also outperform many much larger models, delivering outsized values for their respective compute class. Meanwhile, our most capable and largest model, Reka Core, approaches the best frontier models on both automatic evaluations and blind human evaluations. On image question answering benchmarks (e.g. MMMU, VQAv2), Core performs competitively to GPT4-V. Meanwhile, on multimodal chat, Core ranks as the second most preferred model under a blind third-party human evaluation setup, outperforming other models such as Claude 3 Opus. On text benchmarks, Core not only performs competitively to other frontier models on a set of well-established benchmarks (e.g. MMLU, GSM8K) but also outperforms GPT4-0613 on human evaluation. On video question answering (Perception-Test), Core outperforms Gemini Ultra. Models are shipped in production at http://chat.reka.ai . A showcase of non cherry picked qualitative examples can also be found at http://showcase.reka.ai . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_12387 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Reka Core, Flash, and Edge: A Series of Powerful Multimodal Language Models Reka Team Ormazabal, Aitor Zheng, Che d'Autume, Cyprien de Masson Yogatama, Dani Fu, Deyu Ong, Donovan Chen, Eric Lamprecht, Eugenie Pham, Hai Ong, Isaac Aleksiev, Kaloyan Li, Lei Henderson, Matthew Bain, Max Artetxe, Mikel Relan, Nishant Padlewski, Piotr Liu, Qi Chen, Ren Phua, Samuel Yang, Yazheng Tay, Yi Wang, Yuqi Zhu, Zhongkai Xie, Zhihui Computation and Language Computer Vision and Pattern Recognition We introduce Reka Core, Flash, and Edge, a series of powerful multimodal language models trained from scratch by Reka. Reka models are able to process and reason with text, images, video, and audio inputs. This technical report discusses details of training some of these models and provides comprehensive evaluation results. We show that Reka Edge and Reka Flash are not only state-of-the-art but also outperform many much larger models, delivering outsized values for their respective compute class. Meanwhile, our most capable and largest model, Reka Core, approaches the best frontier models on both automatic evaluations and blind human evaluations. On image question answering benchmarks (e.g. MMMU, VQAv2), Core performs competitively to GPT4-V. Meanwhile, on multimodal chat, Core ranks as the second most preferred model under a blind third-party human evaluation setup, outperforming other models such as Claude 3 Opus. On text benchmarks, Core not only performs competitively to other frontier models on a set of well-established benchmarks (e.g. MMLU, GSM8K) but also outperforms GPT4-0613 on human evaluation. On video question answering (Perception-Test), Core outperforms Gemini Ultra. Models are shipped in production at http://chat.reka.ai . A showcase of non cherry picked qualitative examples can also be found at http://showcase.reka.ai . |
| title | Reka Core, Flash, and Edge: A Series of Powerful Multimodal Language Models |
| topic | Computation and Language Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.12387 |