cogvlm2-llama3-caption

zai-org/cogvlm2-llama3-caption

Video Text To Text12.5B parameterstransformersLicense: other
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
286
Total downloads
309.6K
Gained 7D
+45(increase)
0.0%(up) vs baseline
Gained 30D
—
Likes
119
+0 in 7D
Rank · tracked models
#50,628
206(down 206 places)this week
Parameters
12.5B
Last source update
May 14, 2025
Momentum
23.2
  • cogvlm2-llama3-caption gained 45 downloads during the last seven tracked days.
  • It moved from #48 to #47 among tracked Video Text To Text models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

cogvlm2-llama3-caption is a video text to text model published by zai-org. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it Oct 6, 2026.

Published
Sep 18, 2024
Last updated
May 14, 2025
Library
transformers
License
other
Task
Video Text To Text
Parameters
12,507,532,544
Spaces
—
Derivative models
—
Velocity 7D/day
6
transformerssafetensorstext-generationvideo-text-to-textcustom_codeenarxiv:2408.06072base_model:meta-llama/Llama-3.1-8B-Instructbase_model:finetune:meta-llama/Llama-3.1-8B-Instructlicense:otherregion:us

Publisher

zai-orgView publisher statistics →

Derived from meta-llama/Llama-3.1-8B-Instruct (reported by the source; parent not yet tracked).

Similar models

Models similar to cogvlm2-llama3-caption
ModelDL 30D
MOSS-VL-Instruct-0708-FP8OpenMOSS-Team1,554
MOSS-VL-RealtimeOpenMOSS-Team1,224
MOSS-VL-Instruct-0708OpenMOSS-Team865
MOSS-VL-Instruct-0408OpenMOSS-Team557
MOSS-VL-Realtime-NF4OpenMOSS-Team308
MOSS-VL-Base-0408OpenMOSS-Team130
zai-org/cogvlm2-llama3-caption — Downloads, Growth & Stats | OpenModelStats