Masking-KD

SeonghoonYu/Masking-KD

Image Text to Text2.4B parameterstransformersLicense: apache-2.0

Tracked by OpenModelStats since October 5, 2026View on Hugging Face ↗

Downloads 30D: 4
Total downloads: 4
Gained 7D: —
Gained 30D: —
Likes: 0
Rank · tracked models: —; –this week
Parameters: 2.4B
Last source update: Oct 5, 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 2026-10-05. Charts appear as daily observations accumulate.

Overview

Masking-KD is a image text to text model published by SeonghoonYu. OpenModelStats has tracked the model since Oct 5, 2026, most recently observing it Oct 6, 2026.

Published: Oct 5, 2026
Last updated: Oct 5, 2026
Library: transformers
License: apache-2.0
Task: Image Text to Text
Parameters: 2,438,696,960
Spaces: —
Derivative models: —
Velocity 7D/day: —

transformerssafetensorsqwen3_vlimage-text-to-textknowledge-distillationmultimodal-reasoningconversationaldataset:SeonghoonYu/Masking-KD-Rolloutsarxiv:2605.11651base_model:Qwen/Qwen3-VL-2B-Thinkingbase_model:finetune:Qwen/Qwen3-VL-2B-Thinkinglicense:apache-2.0

Publisher

SeonghoonYuView publisher statistics →

Derived from Qwen/Qwen3-VL-2B-Thinking (reported by the source; parent not yet tracked).

Similar models

Models similar to Masking-KD
Model	Task	DL 30D	Likes	Params
Cosmos-Reason2-2Bnvidia	Image Text to Text	616.3K	290	2.4B
RynnBrain-2BAlibaba-DAMO-Academy	Image Text to Text	28.2K	26	2.4B
UI-Venus-1.5-2BinclusionAI	Image Text to Text	8,139	42	2.4B
CapRL-Qwen3VL-2Binternlm	Image Text to Text	442	16	2.4B
ProcVLM-2Bce-amtic	Image Text to Text	353	0	2.4B
Qwen3-VL-2B-Thinking-FP8Qwen	Image Text to Text	20.4K	34	2.4B