Qwen2-VL-7B-Instruct-AWQ

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

Qwen/Qwen2-VL-7B-Instruct-AWQ

kind: awq
quant: awq
family: qwen
modality: image-text-to-text
root model: Qwen/Qwen2-VL-7B-Instruct
provider: Qwen
license: apache-2.0
language: en
context: —
library: transformers
vRAM (GB): 2
size on disk: —
downloads: 1,809,222
likes: 49
created: —
last modified: 2024-09-25T12:32:39+00:00 (2024)
huggingface: https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct-AWQ
tags: transformerssafetensorsqwen2_vlimage-text-to-textmultimodalconversationalenarxiv:2409.12191arxiv:2308.12966base_model:Qwen/Qwen2-VL-7B-Instructbase_model:quantized:Qwen/Qwen2-VL-7B-Instructlicense:apache-2.0text-generation-inferenceendpoints_compatible4-bitawqregion:us

benchmark	category	score	conf	evidence
DocVQA	multimodal	93.89	high	`\| Qwen2-VL-7B-Instruct \| BF16<br><sup>([🤗](https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct)[🤖](https://modelscope.cn/models/qwen/Qwen2-VL-7B-Instruct)) \| 53.77 \| 93.89 \| 81.78 \| 5`
MMBench	multimodal	81.78	high	`\| Qwen2-VL-7B-Instruct \| BF16<br><sup>([🤗](https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct)[🤖](https://modelscope.cn/models/qwen/Qwen2-VL-7B-Instruct)) \| 53.77 \| 93.89 \| 81.78 \| 5`
MathVista	multimodal	58.2	high	`\| Qwen2-VL-7B-Instruct \| BF16<br><sup>([🤗](https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct)[🤖](https://modelscope.cn/models/qwen/Qwen2-VL-7B-Instruct)) \| 53.77 \| 93.89 \| 81.78 \| 5`
MMMU	multimodal	53.77	high	`\| Qwen2-VL-7B-Instruct \| BF16<br><sup>([🤗](https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct)[🤖](https://modelscope.cn/models/qwen/Qwen2-VL-7B-Instruct)) \| 53.77 \| 93.89 \| 81.78 \| 5`

title	author	status	type
"autoawq" problem	fundayil	open	disc
Update metadata: Add library_name to Transformers	xianbao	merged	disc
config.json breaking change?	matatonic	open	disc
Update generation_config.json	chenkq	merged	disc
ImportError: cannot import name 'Qwen2VLForConditionalGeneration' from 'transformers'	froilo	open	disc
add correct pipeline tag	RaushanTurganbay	merged	disc