Perception-LM-8B

Home/Models/facebook/Perception-LM-8B

facebook/Perception-LM-8B

kind: original
quant: bf16 (16-bit)
family: misc
modality: image-text-to-text
root model: facebook/Perception-LM-8B
provider: facebook
license: other
language: en
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 680
likes: 67
created: —
last modified: 2025-07-14T20:51:54+00:00 (2025)
huggingface: https://huggingface.co/facebook/Perception-LM-8B
tags: safetensorsperception_lmfacebookmetapytorchplmimage-text-to-textconversationalenarxiv:2504.13180license:otherregion:us

benchmark	category	score	conf	evidence
DocVQA	multimodal	90.7	low	`\| PLM1B \| 90.7 \| 78.6 \| 82.1 \| 63.0 \| 84.9 \| 807 \| 138.6 \| 124.2 \| 100.5 \| 34.8 \| 81.7 \| 61.0 \| 59.7 \| 1603 \| 76.3 \| 46.8 \| 73.8 \| 67.1 \| 68.8 \| 88.4 \|`
ChartQA	multimodal	78.6	low	`\| PLM1B \| 90.7 \| 78.6 \| 82.1 \| 63.0 \| 84.9 \| 807 \| 138.6 \| 124.2 \| 100.5 \| 34.8 \| 81.7 \| 61.0 \| 59.7 \| 1603 \| 76.3 \| 46.8 \| 73.8 \| 67.1 \| 68.8 \| 88.4 \|`
MMMU	multimodal	34.8	low	`\| PLM1B \| 90.7 \| 78.6 \| 82.1 \| 63.0 \| 84.9 \| 807 \| 138.6 \| 124.2 \| 100.5 \| 34.8 \| 81.7 \| 61.0 \| 59.7 \| 1603 \| 76.3 \| 46.8 \| 73.8 \| 67.1 \| 68.8 \| 88.4 \|`

none scraped.