Qwen2-VL-72B-Instruct

Home/Models/unsloth/Qwen2-VL-72B-Instruct

unsloth/Qwen2-VL-72B-Instruct

kind: original
quant: bf16 (16-bit)
family: qwen
modality: image-text-to-text
root model: Qwen/Qwen2-VL-72B-Instruct
provider: unsloth
license: apache-2.0
language: en
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 62
likes: 1
created: —
last modified: 2025-03-09T05:06:05+00:00 (2025)
huggingface: https://huggingface.co/unsloth/Qwen2-VL-72B-Instruct
tags: transformerssafetensorsqwen2_vlimage-text-to-textmultimodalqwenqwen2unslothvisionconversationalenarxiv:2409.12191arxiv:2308.12966base_model:Qwen/Qwen2-VL-72B-Instructbase_model:finetune:Qwen/Qwen2-VL-72B-Instructlicense:apache-2.0text-generation-inferenceendpoints_compatibleregion:us

benchmark	category	score	context	conf	evidence
DocVQA	multimodal	86.9	DocVQA<sub>test</sub>	medium	`\| DocVQA<sub>test</sub> \| 86.9 \| - \| 90.1 \|`
ChartQA	multimodal	76.2	ChartQA<sub>test</sub>	medium	`\| ChartQA<sub>test</sub> \| 76.2 \| - \| 73.5 \|`
MMMU	multimodal	36.3	MMMU<sub>val</sub>	medium	`\| MMMU<sub>val</sub> \| 36.3 \| 38.2 \| 41.1 \|`

none scraped.