Eagle2-1B

Home/Models/nvidia/Eagle2-1B

nvidia/Eagle2-1B

kind: merge
quant: merge
family: misc
modality: image-text-to-text
root model: google/paligemma-3b-mix-448
provider: nvidia
license: cc-by-nc-4.0
language: multilingual
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 894
likes: 30
created: —
last modified: 2025-04-27T14:06:42+00:00 (2025)
huggingface: https://huggingface.co/nvidia/Eagle2-1B
tags: transformerssafetensorseagle_2_5_vlfeature-extractioneagleVLMimage-text-to-textconversationalcustom_codemultilingualarxiv:2501.14818base_model:Qwen/Qwen2.5-0.5B-Instructbase_model:merge:Qwen/Qwen2.5-0.5B-Instructbase_model:google/paligemma-3b-mix-448base_model:merge:google/paligemma-3b-mix-448base_model:google/siglip-so400m-patch14-384base_model:merge:google/siglip-so400m-patch14-384license:cc-by-nc-4.0region:us

benchmark	category	score	context	conf	evidence
DocVQA	multimodal	70.0	DocVQA<sub>test</sub>	medium	`\| DocVQA<sub>test</sub> \| 70.0 \| 81.7 \| 84.8 \| 90.1 \| 81.8 \|`
ChartQA	multimodal	61.4	ChartQA<sub>test</sub>	medium	`\| ChartQA<sub>test</sub> \| 61.4 \| 72.9 \| 75.9 \| 73.0 \| 77.0 \|`
MMMU	multimodal	31.4	MMMU<sub>val</sub>	medium	`\| MMMU<sub>val</sub> \| 31.4 \| 36.7 \| 40.9 \| 41.1 \| 38.8 \|`

none scraped.