Qwen2-VL-7B-Instruct

Home/Models/Qwen/Qwen2-VL-7B-Instruct

Qwen/Qwen2-VL-7B-Instruct

kind: original
quant: bf16 (16-bit)
family: qwen
modality: image-text-to-text
root model: Qwen/Qwen2-VL-7B
provider: Qwen
license: apache-2.0
language: en
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 1,519,560
likes: 1,284
created: —
last modified: 2025-02-06T05:18:08+00:00 (2025)
huggingface: https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct
tags: transformerssafetensorsqwen2_vlimage-text-to-textmultimodalconversationalenarxiv:2409.12191arxiv:2308.12966base_model:Qwen/Qwen2-VL-7Bbase_model:finetune:Qwen/Qwen2-VL-7Blicense:apache-2.0eval-resultstext-generation-inferenceendpoints_compatibleregion:usdeploy:sagemaker

benchmark	category	score	context	conf	evidence
DocVQA	multimodal	91.6	DocVQA<sub>test</sub>	medium	`\| DocVQA<sub>test</sub> \| 91.6 \| 90.8 \| - \| 94.5 \|`
ChartQA	multimodal	83.3	ChartQA<sub>test</sub>	medium	`\| ChartQA<sub>test</sub> \| 83.3 \| - \| - \| 83.0 \|`
MMBench	multimodal	81.7	MMBench-EN<sub>test</sub>	medium	`\| MMBench-EN<sub>test</sub> \| 81.7 \| - \| - \| 83.0 \|`
MMBench	multimodal	81.2	MMBench-CN<sub>test</sub>	medium	`\| MMBench-CN<sub>test</sub> \| 81.2 \| - \| - \| 80.5 \|`
MMBench	multimodal	79.4	MMBench-V1.1<sub>test</sub>	medium	`\| MMBench-V1.1<sub>test</sub> \| 79.4 \| 78.0 \| 76.0 \| 80.7 \|`
MT-Bench	chat	63.7	MMT-Bench<sub>test</sub>	medium	`\| MMT-Bench<sub>test</sub> \| - \| - \| - \| 63.7 \|`
MathVista	multimodal	58.3	MathVista<sub>testmini</sub>	medium	`\| MathVista<sub>testmini</sub> \| 58.3 \| 60.6 \| 52.4 \| 58.2 \|`
MMMU	multimodal	51.8	MMMU<sub>val</sub>	medium	`\| MMMU<sub>val</sub> \| 51.8 \| 49.8 \| 60 \| 54.1 \|`

none scraped.