paligemma2-10b-pt-448

Home/Models/google/paligemma2-10b-pt-448

google/paligemma2-10b-pt-448

kind: original
quant: bf16 (16-bit)
family: gemma
modality: image-text-to-text
root model: google/paligemma2-10b-pt-448
provider: google
license: gemma
language: —
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 468
likes: 16
created: —
last modified: 2024-12-05T12:43:00+00:00 (2024)
huggingface: https://huggingface.co/google/paligemma2-10b-pt-448
tags: transformerssafetensorspaligemmaimage-text-to-textarxiv:2407.07726arxiv:2408.00118arxiv:2310.09199arxiv:2303.15343arxiv:1706.03762arxiv:2010.11929arxiv:2412.03555arxiv:2209.06794arxiv:2209.04372arxiv:2103.01913arxiv:1908.04913arxiv:1906.02467arxiv:2203.10244arxiv:2205.12522arxiv:2104.12756arxiv:1608.00272arxiv:1511.02283arxiv:1905.13648arxiv:2110.11624arxiv:2108.03353

benchmark	category	score	context	conf	evidence
ChartQA	multimodal	74.4	[ChartQA][] (aug)	medium	`\| [ChartQA][chartqa] (aug) \| 74.4 \| 74.2 \| 68.9 \| 89.2 \| 90.1 \| 85.1 \|`
ChartQA	multimodal	42.0	[ChartQA][] (human)	medium	`\| [ChartQA][chartqa] (human) \| 42.0 \| 48.4 \| 46.8 \| 54.0 \| 66.4 \| 61.3 \|`
DocVQA	multimodal	39.9	[DocVQA][] (val)	medium	`\| [DocVQA][docvqa] (val) \| 39.9 \| 43.9 \| 44.9 \| 73.6 \| 76.6 \| 76.1 \|`
CER	speech-asr	1.6		low	`\| PaliGemma 2 3B \| 1.6 \| 6.7 \| 2.3 \|`

none scraped.