Qwen2-VL-72B-Instruct-GPTQ-Int8

Home/Models/Qwen/Qwen2-VL-72B-Instruct-GPTQ-Int8

Qwen/Qwen2-VL-72B-Instruct-GPTQ-Int8

kind: gptq
quant: gptq
family: qwen
modality: image-text-to-text
root model: Qwen/Qwen2-VL-72B-Instruct
provider: Qwen
license: other
language: en
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 90
likes: 11
created: —
last modified: 2024-09-24T05:08:42+00:00 (2024)
huggingface: https://huggingface.co/Qwen/Qwen2-VL-72B-Instruct-GPTQ-Int8
tags: safetensorsqwen2_vlmultimodalimage-text-to-textconversationalenarxiv:2308.12966base_model:Qwen/Qwen2-VL-72B-Instructbase_model:quantized:Qwen/Qwen2-VL-72B-Instructlicense:other8-bitgptqregion:us

benchmark	category	score	conf	evidence
DocVQA	multimodal	95.79	high	`\| Qwen2-VL-72B-Instruct \| BF16<br><sup>([🤗](https://huggingface.co/Qwen/Qwen2-VL-72B-Instruct)[🤖](https://modelscope.cn/models/qwen/Qwen2-VL-72B-Instruct)) \| 65.44 \| 95.79 \| 86.94`
MMBench	multimodal	86.94	high	`\| Qwen2-VL-72B-Instruct \| BF16<br><sup>([🤗](https://huggingface.co/Qwen/Qwen2-VL-72B-Instruct)[🤖](https://modelscope.cn/models/qwen/Qwen2-VL-72B-Instruct)) \| 65.44 \| 95.79 \| 86.94`
MathVista	multimodal	70.19	high	`\| Qwen2-VL-72B-Instruct \| BF16<br><sup>([🤗](https://huggingface.co/Qwen/Qwen2-VL-72B-Instruct)[🤖](https://modelscope.cn/models/qwen/Qwen2-VL-72B-Instruct)) \| 65.44 \| 95.79 \| 86.94`
MMMU	multimodal	65.44	high	`\| Qwen2-VL-72B-Instruct \| BF16<br><sup>([🤗](https://huggingface.co/Qwen/Qwen2-VL-72B-Instruct)[🤖](https://modelscope.cn/models/qwen/Qwen2-VL-72B-Instruct)) \| 65.44 \| 95.79 \| 86.94`

none scraped.