Task
Video Text To Text
K
Kwai-Keye/Keye-VL-1_5-8B
Video Text To Text·Kwai-Keye· 211.6K· 69
Keye-VL-1.5 is a cutting-edge Multimodal Large Language Model (MLLM) that addresses fundamental challenges in video comprehension. It features a novel Slow-Fast video encoding strategy, a progressive four-stage pre-training methodology to extend context length up to 128K tokens, and a comprehensive post-training pipeline focusing on reasoning enhancement and human preference alignment. The model d
# pull & run locally
pip install mlforge-sdk && mlforge pull Kwai-Keye/Keye-VL-1_5-8B
pip install mlforge-sdk && mlforge pull Kwai-Keye/Keye-VL-1_5-8B
Model details
Provider
Kwai-Keye
Framework
transformers
Parameters
8.7B
Size
16 GB
License
apache-2.0
Downloads
211.6K
Likes
69
Paper
arXiv:2509.01563
Updated
2026-02-05
About Kwai-Keye/Keye-VL-1_5-8B
Keye-VL-1.5 is a cutting-edge Multimodal Large Language Model (MLLM) that addresses fundamental challenges in video comprehension. It features a novel Slow-Fast video encoding strategy, a progressive four-stage pre-training methodology to extend context length up to 128K tokens, and a comprehensive post-training pipeline focusing on reasoning enhancement and human preference alignment. The model demonstrates significant improvements in video understanding tasks and maintains competitive performance on general multimodal benchmarks.