VideoLLaMA2.1-7B-16F-Base

DAMO-NLP-SG/VideoLLaMA2.1-7B-16F-Base

Visual Question AnsweringtransformersLicense: apache-2.0

Tracked by OpenModelStats since August 31, 2026View on Hugging Face ↗

Downloads 30D: 51
Total downloads: 4,588
Gained 7D: +8(increase); 0.2%(up) vs baseline
Gained 30D: —
Likes: 1; +0 in 7D
Rank · tracked models: #17,257; 125(up 125 places)this week
Parameters: —
Last source update: Oct 21, 2024

VideoLLaMA2.1-7B-16F-Base gained 8 downloads during the last seven tracked days.

7D 30D 90D 1Y All

Total downloads Gained per day Rolling recent downloads

Downloads over time

Daily gain between consecutive observations

Likes over time

Rank among tracked models

Lower is better

Overview

VideoLLaMA2.1-7B-16F-Base is a visual question answering model published by DAMO-NLP-SG. OpenModelStats has tracked the model since Aug 31, 2026, most recently observing it Sep 30, 2026.

Published: Oct 14, 2024
Last updated: Oct 21, 2024
Library: transformers
License: apache-2.0
Task: Visual Question Answering
Parameters: —
Spaces: 0
Derivative models: —
Velocity 7D/day: 1

transformersvideollama2_qwen2text-generationmultimodal large language modellarge video-language modelvisual-question-answeringendataset:OpenGVLab/VideoChat2-ITdataset:Lin-Chen/ShareGPT4Vdataset:liuhaotian/LLaVA-Instruct-150Karxiv:2406.07476arxiv:2306.02858

Publisher

DAMO-NLP-SGView publisher statistics →

Similar models

Models similar to VideoLLaMA2.1-7B-16F-Base
Model	Task	DL 30D	Likes	Params
blip-vqa-baseSalesforce	Visual Question Answering	594.1K	195	385M
vilt-b32-finetuned-vqadandelin	Visual Question Answering	76.3K	425	—
deplotgoogle	Visual Question Answering	23.7K	323	282M
MiniCPM-V-2openbmb	Visual Question Answering	18.2K	504	3.4B
Qwen3.5-2B-MedVLOpenMed	Visual Question Answering	13.9K	14	2.2B
blip-vqa-capfilt-largeSalesforce	Visual Question Answering	12.6K	54	—