vicuna_clip_hybrid

wjdghks950/vicuna_clip_hybrid

Visual Question Answering13.5B parameterstransformers

Tracked by OpenModelStats since October 7, 2026View on Hugging Face ↗

Downloads 30D: 13
Total downloads: 13
Gained 7D: —
Gained 30D: —
Likes: 0
Rank · tracked models: —; –this week
Parameters: 13.5B
Last source update: Oct 7, 2026

7D 30D 90D 1Y All

Total downloads Gained per day Rolling recent downloads

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-10-07. Charts appear as daily observations accumulate.

Overview

vicuna_clip_hybrid is a visual question answering model published by wjdghks950. OpenModelStats has tracked the model since Oct 7, 2026, most recently observing it 28h ago.

Published: Oct 7, 2026
Last updated: Oct 7, 2026
Library: transformers
License: —
Task: Visual Question Answering
Parameters: 13,476,328,497
Spaces: —
Derivative models: —
Velocity 7D/day: —

transformerssafetensorsllava_llamatext-generationmolmultimodalvisual-question-answeringcustom-codeenbase_model:lmsys/vicuna-13b-v1.5base_model:finetune:lmsys/vicuna-13b-v1.5endpoints_compatible

Publisher

wjdghks950View publisher statistics →

Derived from lmsys/vicuna-13b-v1.5 (reported by the source; parent not yet tracked).

Similar models

Models similar to vicuna_clip_hybrid
Model	Task	DL 30D	Likes	Params
MiniCPM-Llama3-V-2_5-int4openbmb	Visual Question Answering	190	80	8.8B
VideoLLaMA2.1-7B-AVDAMO-NLP-SG	Visual Question Answering	2,352	16	8.5B
VideoScore2TIGER-Lab	Visual Question Answering	3,924	5	8.3B
VideoScoreTIGER-Lab	Visual Question Answering	59	8	8.3B
llava-med-v1.5-mistral-7b-hfchaoyinshe	Visual Question Answering	1,390	8	7.6B
MechVL-4B-RLXiaofengAlg	Visual Question Answering	756	4	4.8B